ArticleLiterature Review

Effect Size and Power in Assessing Moderating Effects of Categorical Variables Using Multiple Regression: A 30-Year Review

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

The authors conducted a 30-year review (1969-1998) of the size of moderating effects of categorical variables as assessed using multiple regression. The median observed effect size (f(2)) is only .002, but 72% of the moderator tests reviewed had power of .80 or greater to detect a targeted effect conventionally defined as small. Results suggest the need to minimize the influence of artifacts that produce a downward bias in the observed effect size and put into question the use of conventional definitions of moderating effect sizes. As long as an effect has a meaningful impact, the authors advise researchers to conduct a power analysis and plan future research designs on the basis of smaller and more realistic targeted effect sizes.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... In short, multi-item scales are much more effective in terms of explaining the target construct's variance , which can be particularly problematic in the context of moderation. The reason is that moderation is usually associated with rather limited effect sizes (Aguinis, Beaty, Boik, & Pierce, 2005), so small (but meaningful) effects will be more difficult to identify as significant. Furthermore, when modeling moderating effects, the moderator's measurement model is included twice in the model -in the moderator variable itself and in the interaction term (see the next section). ...
... General guidelines for assessing ƒ 2 suggest values of 0.02, 0.15, and 0.35 represent small, medium, and large effect sizes, respectively (Cohen, 1988). However, Aguinis et al. (2005) have shown that the average effect size in tests of moderation is only 0.009. Against this background, Kenny (2018) proposes that 0.005, 0.01, and 0.025, respectively, constitute more realistic standards for small, medium, and large effect sizes of moderation but also points out that even these values are optimistic. ...
Book
In 2021, the third edition of our introductory book A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM) was published (Hair, Hult, Ringle, & Sarstedt, 2022). The book covers the latest developments in the ield, including recent advances in model evaluation (e.g., inference testing in discriminant validity assessment, predictive power assessments using PLS predict comparisons), improved guidelines for minimum sample sizes, and new complementary methods and concepts such as necessary condition analysis and endogeneity. The book has been highly successful as evidenced in its citation count of more than 24,000 times according to Google Scholar (as of August 2021), and the translations into seven other languages, including in German (Hair et al., 2017), Italian (Hair et al., 2020), and Spanish (Hair et al., 2019). One of the book’s features that has likely contributed to its popularity is our strong focus on pedagogical elements, most notably our reliance on a single running case study and the commercial SmartPLS 3 software (Ringle, Wende, & Becker, 2015), which stands out due to its frictionless design, allowing novice researchers to quickly specify and estimate PLS path models (Memon et al., 2021; Sarstedt & Cheah, 2019).
... (Kirk, 1996), is left in the model because its effect is significant. In addition, the effects of the interaction, both in size effect and statistical power, are lower than those of the main variables; in a revision of scientific publications (Aguinis, Beaty, Boik & Pierce, 2005), the median of all empirical effect sizes has been of .002 (our, of .004, is bigger), and with our effect size of .004, the found median power was of .300 ...
... (and our power is bigger, .540), only the 8.80% of the regression interactions had a power of 80% or more, so the limits for the size of the effect should be lowered (Aguinis, 2004;Aguinis et al., 2005). Therefore, the referred variables and interaction of ours hypotheses are confirmed. ...
Article
Full-text available
There are many studies on Self-Attributed Face-ism (SAF) in considering social networks (SNS), sex and age, but with these variables separately. This research carries out a joint study of the above variables through a random sample of 1050 SNS profiles. Our hypothesis is that SAF is a function of SNS (dating: Badoo, social: Facebook, professional: LinkedIn), sex, age, and the interaction of sex×age. The results show dif-ferences in SAF depending on SNS (highest in the professional network), men having more facial prominence than women. It happens even more when they get older, whereas SAF hardly augments in women with age (having more body prominence than men) (sex x age interaction). Findings show that SAF on-line is a complex phenomenon, it seems not to have a unique and straightforward theoretical explanation, and SAF gender stereotypes grow with age. We also consider the need to study the phenomenon, including a gender perspective, to fight against sexism in new media. Keywords: Self-Attributed. Face-ism. Gender. Age. Social network sites. Self-presentation.
... Accordingly, the MRA may lead to incorrect implications on moderation effects. For example, Aguinis et al. (2005) argue that many researchers have concluded that moderation effects do not exist with the TMRM used in the MRA, despite the pervasive interest in moderators and the theory-based expectation of moderators. ...
... This result implies that previous research based on the MRA might have incorrectly led to conclusions that there did not exist moderation effects even though the moderation effects were strongly supported by theories. It is notable that many researchers have concluded that moderation effects do not exist with the TMRM used in the MRA, despite the pervasive interest in moderators and the theory-based expectation of moderators (Aguinis et al. 2005). The empirical analysis shows that the MRA leads to incorrect conclusions on the moderators specified as the HM type (indicating the Homologizer and the Moderator) about 25%-50% when the MRA is assessed with 200 samples. ...
Article
Full-text available
Previous research has examined moderation effects with traditional analyses such as ANOVA, ANCOVA, moderated regression analysis (MRA), or a combination of MRA and subgroup analysis. However, there exists some confusion in such analyses, because the analyses do not separately consider two possible effects of a moderator on the form and strength of relationship between a focal predictor and a dependent variable. The effect on the form is measured with the interaction effect between the focal predictor and the mod-erator whereas the effect on the strength is measured with the effect of the moderator on predictability of the focal predictor on the dependent variable. This paper proposes a heterogeneous MRA that allows the moderation effect to be heterogeneous in the population, and shows that it allows one to examine the two possible moderation effects separately. Furthermore, this paper shows that previous research based on the traditional analyses might have incorrectly led to conclusions that there did not exist moderation effects even though the moderation effects were strongly supported by theories. The heterogeneous MRA can examine moderation effects with a data set collected for the traditional analyses. Thus, this paper recommends one to use the heterogeneous MRA together with the traditional analyses.
... This study is the first, to our knowledge, to examine the complex relationships among work limitations, worker for the moderating variable (f 2 ) was 0.012, which can be interpreted as a medium effect size [73,74] ...
... A significant positive path coefficient was observed between educational attainment and job crafting (0.064, p = 0.032), suggesting that persons 2 This interpretation of moderation (interaction) effects is different from conventional effect sizes such as Cohen's d. Aguinis and colleagues [74] have established that the average effect size for moderation (interaction) effects is 0.009. Moderation (interaction) effect sizes of 0.005, 0.01, and 0.025 are considered small, medium, and large respectively. ...
Article
Full-text available
Purpose Job crafting is an incremental, employee-initiated job design process used to achieve a better fit between job demands and worker skills. Persons with work limitations face multiple barriers to optimal work performance. Some persons with work limitations may innately use job crafting as a strategy to achieve better alignment with their job tasks and demands, however the extent to which job crafting may be helpful in improving work performance and engagement is unknown. The purpose of this study is (1) to examine the moderating role of work limitations in the relationship between job crafting and work performance and (2) to understand the complex relationship between job crafting, work limitations, work engagement, work performance, readiness to change, and worker characteristics. Methods We conducted an online survey of workers with and without disabilities (final N = 742) in 2020–2021. Our sample included workers aged 18 and older. Descriptive statistics, bivariate statistics, and Partial Least Squares-Structural Equation Modeling (PLS-SEM) were used to assess the relationships among job crafting, work limitations, work engagement, work performance, readiness to change, and worker characteristics. Results Work limitation moderates the relationship between job crafting and work performance by weakening the impact of innate job crafting on work performance. Worker characteristics such as education and years of work experience predict crafting behaviors and work engagement mediates the relationship between job crafting and work performance. Conclusions Work limitation weakens the relationship between job crafting and work performance. Workers with limitations may benefit from job crafting interventions to increase work engagement and performance.
... Interactions are widely tested across the psychological and social sciences, yet there is growing concern that they contribute to the low replicability of findings in these fields (Altmejd et al., 2019;Open Science Collaboration, 2015). In tandem, there is increasing evidence that the effect sizes of interactions in observational designs are quite small (Aguinis et al., 2005;Beck & Jackson, 2020;Sherman & Pashler, 2019;Tosh et al., 2021;Vize et al., 2022). In the context of these concerns, power analyses can be a critically useful tool for ensuring the robustness and accuracy of conclusions resulting from tests of interactions. ...
... It should also be noted that prior work has found that interaction effects are commonly quite small. In review of 261 papers in psychology journals which reported interaction effects, Aguinis et al. found a median effect of ƒ 2 =0.002 (approximately r=0.044) (Aguinis et al., 2005). Recent work in personality science suggests that most replicable interaction effects are in fact smaller than this (Vize et al., 2022). ...
Preprint
Full-text available
Interaction analyses (also termed ‘moderation’ analyses or ‘moderated multiple regression’) are a form of linear regression analysis designed to test whether the association between two variables changes when conditioned on a third variable. It can be challenging to perform a power analysis for interactions with existing software, particularly when variables are correlated and continuous. Moreover, while power is impacted by variable parameters that are always present in cross-sectional observational studies, such as reliability and skew, it can be unclear how to incorporate these effects into a power analysis. The R package InteractionPoweR and associated Shiny app allow researchers with minimal or no programming experience to perform analytic and simulation-based power analyses for interactions. At minimum, these analyses require the Pearson’s correlation between variables and sample size, and parameters including reliability, skew, and the number of discrete levels that a variable takes (e.g., binary or likert scale) can optionally be specified. In this Tutorial we demonstrate how to perform power analyses using our package and give examples of how power can be impacted by main effects, correlations between main effects, reliability, and variable distributions. We close with a brief discussion of how researchers may select an appropriate interaction effect size when performing a power analysis.
... Third, as the data was collected from four Europe countries (namely, Italy, Finland, Portugal and Israel) caution should be taken in generalization of the present data, due to cultural invariance as somatic symptoms can vary across cultures (Ma-Kellams, 2014). Finally, the effect sizes of the PACT subscales are rather modest in magnitude (Aguinis et al., 2005). However, we consider them non-negligible as they reflect only one of the numerous coping mechanisms patients can employ in context of the illness. ...
Article
Objective The current study assessed breast cancer patients' somatic symptoms during the first six months post diagnosis and examined the moderating role of coping flexibility (i.e., trauma-focused and forward-focused coping strategies) on the association between reported somatic symptoms three months after breast cancer diagnosis and somatic symptoms six months after diagnosis. Method and measures An international sample of 702 women diagnosed with breast cancer from four countries (Finland, Israel, Italy, Portugal) completed self-reported questionnaires at three time points: at the time of diagnosis (M0), three months post diagnosis (M3), and six months post diagnosis (M6). The questionnaires included the coping flexibility scale and questions about demographics, medical data, and somatic symptoms. Results The highest level of somatic symptoms was reported after three months post diagnosis (M3), as compared to M0 and M6. Both trauma-focused and forward-focused coping strategies moderated the relationship between somatic symptoms at M3 and somatic symptoms at M6. Conclusion The findings highlight the importance of assessing somatic symptoms soon after breast cancer diagnosis and throughout the early phase of treatment. Coping flexibility can buffer the stability of the somatic symptoms during this initial phase.
... In a follow-up analysis, the differences in the log-likelihood ratio value between M0 (main model) and M1 (interaction model) for the three interaction models were all greater than the suggested significance level of 3.84 (df = 1, p < .001). In addition, the differences in the amount of variance explained in attractions (R 2 ) between each pair of M0 and M1 exceeded the median effect size of 0.002 (Aguinis et al., 2005). Overall, the results showed that social distance had a significant moderating effect on the relationships between the three IFA groups and the attractions, partially supporting H5. ...
Article
Given the growing importance of social media (SM) for tourism promotions, the present study examined a destination image model that includes SM as image formation agents (IFAs) (autono-mous, induced, and organic), cognitive image (attractions and support), affective image, and social distance as a moderator, grounded in construal level theory. With the sample of tourists (N = 699), structural equation modeling revealed that each IFA group had different patterns of effects in shaping cognitive image, which in turn influenced affective image. Latent moderated structural equation modeling analysis showed that social distance had a negative interacting effect with each of the IFA groups in forming the attractions image, highlighting the significant moderating role of social distance in the process. This study enriches an understanding on the crucial roles of IFAs and social distance in the image formation process within the SM context. ARTICLE HISTORY
... We also determined the substantive explanatory contribution of the moderators. Meta-studies in management found that small effect sizes are a reoccurring pattern for moderating variables (Aguinis et al. 2005). The effect sizes of the two significant interaction terms on job meaningfulness are small to medium (task variety x IT support in CI: 0.053, feedback x IT support in CI: 0.043). ...
Thesis
Full-text available
Traditional organizations are strongly encouraged by emerging digital customer behavior and digital competition to transform their businesses for the digital age. Incumbents are particularly exposed to the field of tension between maintaining and renewing their business model. Banking is one of the industries most affected by digitalization, with a large stream of digital innovations around Fintech. Most research contributions focus on digital innovations, such as Fintech, but there are only a few studies on the related challenges and perspectives of incumbent organizations, such as traditional banks. Against this background, this dissertation examines the specific causes, effects and solutions for traditional banks in digital transformation − an underrepresented research area so far. The first part of the thesis examines how digitalization has changed the latent customer expectations in banking and studies the underlying technological drivers of evolving business-to-consumer (B2C) business models. Online consumer reviews are systematized to identify latent concepts of customer behavior and future decision paths as strategic digitalization effects. Furthermore, the service attribute preferences, the impact of influencing factors and the underlying customer segments are uncovered for checking accounts in a discrete choice experiment. The dissertation contributes here to customer behavior research in digital transformation, moving beyond the technology acceptance model. In addition, the dissertation systematizes value proposition types in the evolving discourse around smart products and services as key drivers of business models and market power in the platform economy. The second part of the thesis focuses on the effects of digital transformation on the strategy development of financial service providers, which are classified along with their firm performance levels. Standard types are derived based on fuzzy-set qualitative comparative analysis (fsQCA), with facade digitalization as one typical standard type for low performing incumbent banks that lack a holistic strategic response to digital transformation. Based on this, the contradictory impact of digitalization measures on key business figures is examined for German savings banks, confirming that the shift towards digital customer interaction was not accompanied by new revenue models diminishing bank profitability. The dissertation further contributes to the discourse on digitalized work designs and the consequences for job perceptions in banking customer advisory. The threefold impact of the IT support perceived in customer interaction on the job satisfaction of customer advisors is disentangled. In the third part of the dissertation, solutions are developed design-oriented for core action areas of digitalized business models, i.e., data and platforms. A consolidated taxonomy for data-driven business models and a future reference model for digital banking have been developed. The impact of the platform economy is demonstrated here using the example of the market entry by Bigtech. The role-based e3-value modeling is extended by meta-roles and role segments and linked to value co-creation mapping in VDML. In this way, the dissertation extends enterprise modeling research on platform ecosystems and value co-creation using the example of banking.
... A moderate effect size was selected for this calculation because, to our knowledge, no previous research has examined the relationship between anxiety disorders and vaccine hesitancy. A concern with moderation analyses that include categorical predictors is that statistical artifacts can prevent researchers from detecting significant effects in their sample, when a significant effect does exist in the population (Aguinis et al., 2005). The high multicollinearity between the interaction term and its individual predictor terms also inflates the SE and makes interactions difficult to detect. ...
Article
Development of the COVID-19 vaccines unfolded in real-time, lending a sense that they were developed more rapidly than other vaccines. Long-term data on their safety and effectiveness is not yet available. Thus, people may have greater uncertainty about the COVID-19 vaccines than other vaccines. We know that people high in anxiety have greater intolerance of uncertainty (IUS) and may have greater fears of adverse effects and concerns about the vaccine failing to prevent COVID-19. Ultimately, people with anxiety disorders may have greater COVID-19 vaccine hesitancy (VH). This study examined the degree of VH in people with (n = 96) and without (n = 52) anxiety disorders, whether anxiety status has an additive effect on factors known to predict hesitancy, and whether reasons for VH differed across groups. Groups did not differ in VH, but IUS was associated with greater hesitancy in those without anxiety but with less hesitancy in those with anxiety. Both groups’ strongest predictors of hesitancy were influenza vaccine history, conspiracy beliefs, individualism, and trust. The top reasons for VH were concerns about adverse effects and efficacy, and the top reasons to get the vaccine were to protect others and self. Implications for reducing VH are discussed.
... In addition to the cultural differences, we also performed a test for the temporal moderating effect of the publication year. Following Aguinis et al. (2005), we tested the temporal moderating effect by calculating the correlation coefficients between the year of publication and the effect size. For this purpose, median-centered publication years were used as the input instead of the absolute values to enhance the meaningfulness of the intercept and the visibility of the plots (Suurmond et al., 2017). ...
Article
Full-text available
The theory of planned behavior (TPB) is popular in social commerce research, but existing studies have yielded inconclusive and inconsistent findings. As TPB was developed before the introduction of the Internet, Web 2.0 technologies, and social media, it is time to evaluate whether its relevance, effectiveness, novelty, and parsimony may have deteriorated due to temporal factors and the emergence of new Information Systems (IS) artifacts. In this work, an extended TPB2 is proposed by integrating social support, and MASEM analysis was conducted using a pooled correlation matrix. The findings revealed that TPB2 can better capture the nature of social commerce, as it can explain 28.4% of the variance in attitude, 59.0% of the variance in behavioral intention, and 9% of the variance in use behavior. In addition, it indicates that masculinity and uncertainty avoidance are the most significant Hofstedian cultural dimensions. The theoretical and managerial implications are also discussed along with the research agenda.
... When β 71 , the social propaganda policy coefficient is >0 and significant, it indicates that hypothesis H2 is supported. This study analyzes the mediating effect of public green travel attitude by referring to the test methods of mediating effect of many existing studies (Baron and Kenny, 1986;Wen et al., 2004;Aguinis et al., 2005;Chawla and Joshi, 2018). Taking public attitude, subjective norms, and perceived behavior control into the model together with social propaganda policies can test their impact on green travel intention. ...
Article
Full-text available
Social propaganda and guidance policies have important practical significance for promoting public green travel. In recent years, the rapid development of digital technology, network, and mobile communication technology has promoted a revolutionary change in the dissemination of information and services. However, in the era of new media communication driven by emerging technologies, there is still a lack of research on the impact of social propaganda and guidance policies on public willingness to travel green. Based on the theory of planned behavior and the survey research of China's urban residents, this study investigates the impact of social propaganda and guidance policies on public willingness to travel green. Regression analysis is used to identify the influencing factors of public green travel willingness, and to reveal the internal impact mechanism of social propaganda and guidance policies on public green travel willingness. The mediating role of public green travel attitude, subjective norm, and perceived behavior control in social propaganda and guidance policy and travel willingness are also empirically analyzed. The results show that social propaganda and guidance policies have a significant positive impact on green travel attitudes, subjective norms, perceived behavior control, and green travel intentions. Green travel attitude, subjective norm, and perceived behavior control play a mediating role in the relationship between social propaganda and guiding policies and green travel willingness, but the mediating effect of the subjective norm is relatively weak.
... Although our research demonstrated that both PIA and JS served as boundary conditions in the daily association between workaholism and work-family outcomes, the interaction effects found in the study were small. Aguinis et al. (2005) argued that design, measurement, and statistical artefacts may downwardly bias moderating effects, so much so that these effects may not emerge in field studies. We also suspect that these small moderating effects may be due to the fact that our participants reported low scores on WFC. ...
Article
Workaholism is increasingly recognized as a potential threat to occupational health. Although most research has conceptualized workaholism as a trait, some research suggests that it also may fluctuate from day to day. Moreover, the effects of the dynamic properties of workaholism on work and family outcomes may be contingent on one’s economic situation. Therefore, the aim of the present study was to test the interactive effect of workday workaholism and economic resources on nightly work‐family conflict and family engagement. Using experience sampling methodology, we demonstrated that workaholism fluctuates from one day to the next and has detrimental short‐term effects on work‐family conflict. Additionally, our findings indicated that the interaction between workday workaholism and perceived income inadequacy predicted both nighty work‐family conflict and family engagement. While the association between workday workaholism and work‐family conflict was stronger for those who experienced low perceived income adequacy, the relationship between workaholism and family engagement was stronger for those who exhibited high income adequacy. Similarly, job security buffered the effect of workaholism on work‐family conflict. We discuss the theoretical and practice implications of this study as well as recommend future research directions. This article is protected by copyright. All rights reserved.
... (or .0019 when converted to η 2 ), although most of the tests had sufficient power to detect the small effects (Aguinis et al., 2005). Simulation research (e.g., Aguinis & Stone-Romero, 1997) also suggests that interaction effects tend to be underestimated due to research designs and statistical artifacts. ...
Article
For almost 50 years, psychologists have understood that what is beautiful is perceived as good. This simple and intuitively appealing hypothesis has been confirmed in many ways, prompting a wide range of studies documenting the depth and breadth of its truth. Yet, for what is arguably one of the most important forms of "goodness" that there is-moral goodness-research has told a different story. Although greater attractiveness is associated with a host of positive attributes, it has been only inconsistently associated with greater perceived morality (or lesser immorality), and meta-analyses have suggested the total effect of beauty on moral judgment is near zero. The current research documents one plausible reason for this. Across nine experiments employing a variety of methodological and measurement strategies, we show how attractiveness can be perceived as both morally good and bad. We found that attractiveness causally influences beliefs about vanity, which translates into beliefs that more attractive targets are less moral and more immoral. Then, we document a positive association between attractiveness and sociability-the nonmoral component of warmth-and show how sociability exerts a countervailing positive effect on moral judgments. Likewise, we document findings suggesting that vanity and sociability mutually suppress the effects of attractiveness on each other and on moral judgments. Ultimately, this work provides a comprehensive process account of why beauty seems good but can also be perceived as less moral and more immoral, highlighting complex interrelations among different elements of person perception. (PsycInfo Database Record (c) 2022 APA, all rights reserved).
... Finally, on an effect size metric, the magnitude of the interaction was subtle; the model with the interaction term explained slightly more variance in BED symptoms when compared to the model without, improving the R 2 effect size from 0.056 (standard deviation = 0.006) to 0.058 (standard deviation = 0.007). The 0.002 R 2 -change effect size (f 2 = 0.002) represents a small effect-meta-analyses report average effect sizes for interaction terms to be 0.009 (Aguinis, Beaty, Boik, & Pierce, 2005), and suggest benchmarks of 0.005, 0.01, and 0.025 for small, medium, and large effects, respectively (Kenny, 2018). In the uncontrolled model that .4 ...
Article
Although it has been demonstrated that (a) body dissatisfaction and internalization of societal appearance standards contribute to disordered eating and (b) that internalization of societal appearance standards leads to decreased skin color satisfaction among Black women, it has not been established whether skin color dissatisfaction contributes to disordered eating among Black women or girls. The objective of the present study is to determine the influence of skin color satisfaction as a potential predictor for binge eating, and its effect through body image in Black girls during the vulnerable developmental period of adolescence. Using data from ten annual measurements in 1213 Black girls across ages 10–19, we sought to determine whether skin color satisfaction predicts Binge Eating Disorder (BED) risk and symptoms using pre-registered logistic and multilevel models. We found that lower skin color satisfaction at ages 13 and 14 significantly predicted greater odds of BED and lower skin color satisfaction at all ages predicted greater BED symptoms. Body satisfaction mediated the relationship between skin color satisfaction and BED symptoms. Our results suggest that skin color dissatisfaction is a novel component of body image for Black girls that is also related to binge eating.
... For virtually everyone else in this study, regression slopes are so similar and so flat that the predicted value of feedback seeking will be near the mean regardless of the perspective-taking score. Generally, when interaction effects are small, as is the norm in management and related fields (Aguinis, Beaty, Boik, & Pierce, 2005), their theoretical and practical significance will often be felt by only that subset of the sample that is at or near the extreme values for the moderator. ...
Article
Full-text available
Most management theories include hypotheses about interaction effects (i.e., the relation between two variables depends on values of another), but it is common for articles to present results that make it difficult to evaluate the nature, strength, and importance of the effect. We offer recommendations for improving the reporting of interaction effects by focusing on (a) visualizations, (b) effect size estimates, and (c) assessments of the nature, meaning, and importance of interactions for theory and practice.
... In Table 8, we have computed the group with a Z-score as an indication of significance. The effect size of R 2 for MPLe is large, with 0.4324 (f-squared) from an R 2 difference between 0.63 (male) and 0.47 (female) [95,96]. The standardized coefficient for males is −0.24, while the coefficient for females is −0.21. ...
Article
Full-text available
Land-based plastic pollution has increased to the level of an epidemic due to improper plastic waste management, attributed to plastic waste flux into the marine environment. The extant marine plastic litter (MPL) literature focuses primarily on the monitoring and assessment of the problem, but it fails to acknowledge the link between the challenges and opportunities for MPL reduction. The study aimed to examine the practical challenges and opportunities influencing the reduction of marine plastic litter in Manila in the Philippines. Data collected through an online survey from 426 barangays were analyzed using structural equation modeling (SEM) and were then validated using interviews and focused group discussions. Good internal consistency (0.917) and convergent and discriminant validity were achieved. The empirical study has established structural model fit measures of RMSEA (0.021), SRMR (0.015), CFI (0.999), and TLI (0.994), with a good parsimonious fit of the chi-square/degrees of freedom ratio of 1.190. The findings revealed that environmental governance regarding waste management policies and guidelines, COVID-19 regulations for waste management, community participation, and socio-economic activities have positively affected marine plastic litter leakage and solution measures. Environmental governance significantly and partially mediates the effects of, e.g., COVID-19-related waste and socio-economic activities on MPL leakage. However, there is no relationship between the waste management infrastructure and environmental governance. The findings shed light on how to enhance environmental governance to reduce marine plastic litter and address Manila’s practical challenges. [research paper link: https://www.mdpi.com/1636556]
... Contrary to Cohen's recommendation, Kenny (2018) argues that these effect size values are unrealistic. Kenny's argument was based on a review by Aguinis, Beaty, Boik, and Pierce (2005) as cited in Kenny (2018) which showed that the average effect size in the moderation test is only 0.009. Kenny (2018) therefore recommended new realistic values of effect sizes thus 0.005, 0.01, and 0.025 for small, medium, and large, respectively. ...
Article
Full-text available
Many educators are concerned about students’ use of WhatsApp for learning purposes, especially in emergency remote teaching during the COVID-19 pandemic. This study applied the unified theory of acceptance and use of technology (UTAUT) model to examine factors that predict distance students’ acceptance of WhatsApp for learning. Correlational design was employed. Questionnaires were used to collect data from 273 undergraduate and post-graduate diploma distance students in Ghana. Data were analyzed using partial least squares-structural equation modeling (PLS-SEM). The results showed that performance expectancy, effort expectancy, social influence, and facilitating conditions are significant predictors of distance students’ intentions to use WhatsApp to support learning. However, mobile phone self-efficacy without mediation was not a significant predictor of behavioral intention. Finally, use behavior was significantly predicted by behavioral intention but not facilitating conditions. It was recommended, among other things, that before adopting WhatsApp for instructional activities, management and faculties of educational institutions should ensure the availability of suitable conditions such as WhatsApp-supported mobile devices for students’ use.
... Consistent with our prediction, the wealthy versus middle-income difference was also significant, t (1242) We acknowledge that effect sizes were small for BJW × wealth interaction in Experiments 5-6. However, like many social science studies, the observed effect sizes may be underestimated for interaction effects due to design and statistical artifacts (Aguinis, Beaty, Boik, & Pierce, 2005;Aguinis & Stone-Romero, 1997). We additionally note that for our dependent measures of interest (i.e., perceived deservingness and schadenfreude), hypothesized main effects and simple main effects of target BJW had effect sizes ranging from d = 0.20 to d = 0.72, which are non-negligible. ...
Article
When witnessing misfortunes, people sometimes react with schadenfreude—malicious pleasure at another's suffering. Previous research suggests that schadenfreude is elicited for competitors and envied targets, or when misfortunes seem deserved. Six experiments (five pre-registered, N-total = 3324) support a novel hypothesis that perceivers feel greater schadenfreude for social targets who endorse a strong general belief in a just world (BJW), even when misfortunes occur outside of the typical conditions that elicit schadenfreude. Experiments 1–2 show that people feel schadenfreude at the accidental misfortune of a person who expresses strong BJW, based in part on their misfortune seeming more deserved. Experiment 3 demonstrates the same effect for a wealthy, strong-BJW target who suffers a life-changing misfortune. In Experiment 4, we demonstrate that perceivers infer stronger BJW from a wealthy (vs. poor) person and that these inferences lead to increased perceptions that the misfortune was deserved, resulting in greater schadenfreude. Finally, Experiments 5–6 show that the effect of target BJW on schadenfreude via perceived deservingness is moderated by a target's financial status, such that endorsing strong BJW is particularly consequential for wealthy and middle-income targets. We conclude that even when people are not responsible for their predicaments, perceivers believe the misfortunes of people with strong just-world beliefs are more fitting and therefore derive more pleasure at their expense. The current research builds on and extends both schadenfreude and just-world belief literatures by documenting a unique antecedent of schadenfreude based on perceivers' inferences or knowledge regarding how someone generally views their world.
... The effect size of moderation was assessed with f-square, the ratio between the variation explained by the interaction term and the total variation of the dependent variable in question (Aiken & Stephen, 1991). A meta-analysis of previously published research utilising moderation models found that the average effect size of moderation is 0.009, much lower than that of small direct effects of around 0.02 (Aguinis et al., 2005). As per Kenny's (2016), the interaction effect size of moderating factors is small when f-square =.005, medium when f-square =.01 and large when f-square =.025. ...
Article
The COVID-19 pandemic has resulted in countries reacting differently to an ongoing crisis situation. Latent to this reaction mechanism is the inherent cultural characteristics of each society resulting in differential responses to epidemic spread. Epidemiological studies have confirmed the positive effect of population mobility on the growth of infection. However, the effect of culture on indigenous mobility patterns during pandemics needs further investigation. This study aims to bridge this gap by exploring the moderating role of country culture on the relationship between population mobility and growth of CoVID-19. Hofstede’s cultural factors; power distance, individualism/ collectivism, masculinity/femininity, uncertainty avoidance, long-term and short-term orientation are hypothesised to moderate the effect of mobility on the reproduction number (R) of COVID-19. Panel regression model, using mobility data and number of confirmed cases across 95 countries for a period of 170 days has been preferred to test the hypotheses. The results are further substantiated using slope analysis and Johnson-Neyman technique. The findings suggest that as power distance, individualism and long-term orientation scores increase, the impact of mobility on epidemic growth decreases. However, masculinity scores in a society have an opposite moderating impact on epidemic growth rate. These Hofstede factors act as quasi moderators affecting mobility and epidemic growth. Similar conclusions could be not be confirmed for uncertainty avoidance. Cross-cultural impact, as elucidated by this study, forms a crucial element in policy formulation on epidemic control by indigenous Governing bodies.
... Also, the interaction effect sizes are rather weak when applying the standards of Cohen (1988) for direct effects. However, compared to published interaction effect sizes, the interaction effect sizes observed in this essay have to be interpreted as medium to large (Aguinis, Beaty, Boik and Pierce, 2005;Kenny, 2015). Furthermore, the arousal level is not manipulated in isolation (e.g., a recalled positive experience could either be a thrilling bungee jump experience with high arousal levels, or a relaxing sauna visit with low arousal levels). ...
Thesis
Due to the advances of digitalization, firms are able to collect more and more personal consumer data and strive to do so. Moreover, many firms nowadays have a data sharing cooperation with other firms, so consumer data is shared with third parties. Accordingly, consumers are confronted regularly with the decision whether to disclose personal data to such a data sharing cooperation (DSC). Despite privacy research has become highly important, peculiarities of such disclosure settings with a DSC between firms have been neglected until now. To address this gap is the first research objective in this thesis. Another underexplored aspect in privacy research is the impact of low-cognitive-effort decision-making. This is because the privacy calculus, the most dominant theory in privacy research, assumes for consumers a purely cognitive effortful and deliberative disclosure decision-making process. Therefore, to expand this perspective and examine the impact of low-cognitive-effort decision-making is the second research objective in this thesis. Additionally, with the third research objective, this thesis strives to unify and increase the understanding of perceived privacy risks and privacy concerns which are the two major antecedents that reduce consumers’ disclosure willingness. To this end, five studies are conducted: i) essay 1 examines and compares consumers’ privacy risk perception in a DSC disclosure setting with disclosure settings that include no DSC, ii) essay 2 examines whether in a DSC disclosure setting consumers rely more strongly on low-cognitive-effort processing for their disclosure decision, iii) essay 3 explores different consumer groups that vary in their perception of how a DSC affects their privacy risks, iv) essay 4 refines the understanding of privacy concerns and privacy risks and examines via meta-analysis the varying effect sizes of privacy concerns and privacy risks on privacy behavior depending on the applied measurement approach, v) essay 5 examines via autobiographical recall the effects of consumers’ feelings and arousal on disclosure willingness. Overall, this thesis shines light on consumers’ personal data disclosure decision-making: essay 1 shows that the perceived risk associated with a disclosure in a DSC setting is not necessarily higher than to an identical firm without DSC. Also, essay 3 indicates that only for the smallest share of consumers a DSC has a negative impact on their disclosure willingness and that one third of consumers do not intensively think about consequences for their privacy risks arising through a DSC. Additionally, essay 2 shows that a stronger reliance on low-cognitive-effort processing is prevalent in DSC disclosure settings. Moreover, essay 5 displays that even unrelated feelings of consumers can impact their disclosure willingness, but the effect direction also depends on consumers’ arousal level. This thesis contributes in three ways to theory: i) it shines light on peculiarities of DSC disclosure settings, ii) it suggests mechanisms and results of low-effort processing, and iii) it enhances the understanding of perceived privacy risks and privacy concerns as well as their resulting effect sizes. Besides theoretical contributions, this thesis offers practical implications as well: it allows firms to adjust the disclosure setting and the communication with their consumers in a way that makes them more successful in data collection. It also shows that firms do not need to be too anxious about a reduced disclosure willingness due to being part of a DSC. However, it also helps consumers themselves by showing in which circumstances they are most vulnerable to disclose personal data. That consumers become conscious of situations in which they are especially vulnerable to disclose data could serve as a countermeasure: this could prevent that consumers disclose too much data and regret it afterwards. Similarly, this thesis serves as a thought-provoking input for regulators as it emphasizes the importance of low-cognitive-effort processing for consumers’ decision-making, thus regulators may be able to consider this in the future. In sum, this thesis expands knowledge on how consumers decide whether to disclose personal data, especially in DSC settings and regarding low-cognitive-effort processing. It offers a more unified understanding for antecedents of disclosure willingness as well as for consumers’ disclosure decision-making processes. This thesis opens up new research avenues and serves as groundwork, in particular for more research on data disclosures in DSC settings.
... Figure 2 shows that in young ventures, the increase of employees' turnover intent over time is weaker for employees with longer work experience in start-ups prior to the current one, as predicted in Hypothesis 2. Moreover, simple slope analysis shows that there is a significant positive relationship between time and employees' turnover intent when start-up work experience is low (simple slope = 0.327, p < 0.001) A. Domurath et al. and when start-up work experience is high (simple slope = 0.203, p < 0.001). 1 The interaction between time and start-up work experience explains 6% of the slope variance at level 2 (explained slope variance was calculated based on Aguinis et al., 2013), corresponding to a weak interaction effect (e.g., Aguinis et al., 2005). In practical terms, the interaction plot reveals that over a period of 1 year, turnover intent for employees with lower start-up work experience increased by 34.71%. ...
Article
Full-text available
A defining characteristic of young ventures is that they are more likely to experience periods of change (of both a positive and negative nature) than are established organizations. This could result in a misalignment between employees’ expectations when hired and actual work experiences. Based on met expectations theory, we argue that employees’ experiences in young ventures result in greater turnover intent over time. We further theorize that the relationship between time and turnover intent is contingent on employees’ prior work experience at a start-up and venture growth rates. Using a unique longitudinal data set containing 1,151 survey responses from 458 employees of 67 ventures, we find that employees’ turnover intent increases over time and that this effect is particularly strong for employees with little prior start-up work experience and employees working in low-growth ventures. We discuss implications for the literature on employees in entrepreneurial firms.
... This finding is consistent with previous research identifying the benefits of listening for reducing stress and its related aversive feelings such as state anxiety (Itzchakov, 2020), state social anxiety (Itzchakov et al., 2018;Itzchakov & Kluger, 2017b;Itzchakov et al., 2017), and negative affect (Lloyd, Boer, Kluger, et al., 2015). Although the magnitude of the interaction effect size, .04, is small according to (Cohen, 1988), a 30-year review of 261 interaction effects in applied psychology and management indicates that it is in the 88.90 th percentile (Aguinis et al., 2005). ...
Article
Full-text available
When principals listen to their teachers, they may foster an open and receptive work environment that helps teachers adapt during stressful times. Two studies examined the role of perceived principals' listening to teachers on workplace outcomes. Study 1 (N = 218) was conducted during the first nationwide lockdown in Israel. Study 2 (N = 247) was conducted during a later lockdown and controlled for social support to test the independent effects of the two distinct interpersonal experiences. Findings supported our hypothesis that principals' listening would relate to lower teacher turnover intention. In addition, in line with our hypothesis, teachers high on perceived stress generally reported higher turnover intentions. However, the detrimental effect of perceived stress was not observed when teachers evaluated their principals as good listeners. Finally, we anticipated and found that principal listening is associated with organizational citizenship behavior. Specifically, teachers were more likely to help one another when feeling listened to by their principals.
... Thought experiments offer a unique method to consider how a large scope of multiple factors interact simultaneously, particularly how business, legal, and societal challenges impact the "supreme problem" of selection and recruitment (Hall, 1917;Ployhart et al., 2017). Individual difference-outcome relationships remain a concern for OB and human resource management researchers (Aguinis et al., 2005;Le et al., 2011). Additionally, the context in which personnel research is carried out is particularly sensitive, and results are difficult to generalize (Ployhart et al., 2017). ...
Article
Full-text available
Thought experiments have been used as an effective methodological approach to advance theory in numerous scientific fields. However, they are underutilized in organizational behavior (OB) and adjacent fields. Accordingly, we conducted a comprehensive and multidisciplinary literature review of thought experiments that entailed 174 sources in economics, psychology, marketing, medicine, sociology, finance, and other fields. We leveraged insights from this literature review to define and describe the unique nature of thought experiments and offer a taxonomy of four main types based on a theory’s development stage (i.e., early vs. late) and a study’s theoretical goal (i.e., confirmation vs. disconfirmation). We also provide a decision‐making tree useful for evaluating whether conducting a thought experiment is beneficial for a particular research situation and which of the four types is most likely to produce a meaningful contribution. Then, we offer best‐practice recommendations for conducting thought experiments that address how to plan, execute, report results, and discuss implications. In addition, we demonstrate the potential of thought experiments by using the best‐practice recommendations to design and conduct a thought experiment in the domain of workplace allyship. Finally, we offer suggestions for future substantive research that would benefit from thought experiment methodology (e.g., diversity and inclusion, leadership, performance, selection and recruitment, teams, and turnover). Overall, our article offers a comprehensive review and recommendations that we hope will be a catalyst for using thought experiments to advance theory in OB and related fields.
... In fact, it is indisputable that the overall, observed moderating effects usually are smaller than what is conventionally defined as a small effect. 82 Smaller effect size may therefore be of theoretical importance if it supports the theoretical views being tested. Moreover, the interaction effect between classroom environment variables and academic achievement on academic self-concept has been reported in other studies. ...
Article
Full-text available
Purpose: Substantial literature has documented the influence of classroom environment on academic enjoyment. However, little is known about the mediating and moderating mechanisms underlying this relationship. Based on the control-value theory and the individual-context interaction model, a moderated mediation model was constructed in this study to further examine whether academic self-concept mediated the relation between classroom environment and enjoyment in mathematics and whether this mediating effect was moderated by academic achievement. Methods: We recruited 750 Chinese middle school students and they completed the classroom environment, academic self-concept, and academic enjoyment questionnaires. Results: After controlling for gender and grade, the results of structural equation modeling showed that academic self-concept partially mediated the association between classroom environment and enjoyment in mathematics. The mediating path from classroom environment to academic self-concept was moderated by academic achievement. Classroom environment positively predicted academic self-concept for the higher achieving students. However, the effect of classroom environment on academic self-concept was not significant for the lower achieving students. Conclusion: These findings highlight that classroom environment has a more salient impact on academic self-concept and enjoyment for higher achieving students than for lower achieving students. The study results provide guidelines for educators regarding effective interventions for fostering positive academic emotions.
... The effect size (f 2 = .012) is just under the cutoff for a small effect size according to Cohen; 49 however, a review by Agunis and associates 50 found the effect sizes were rarely achieved. Kenny 51 advocated for f 2 effect sizes of .005, ...
Article
Objective: Childhood maltreatment has been consistently linked to posttraumatic stress disorder (PTSD) symptoms among college students and yoga may buffer the effects. The current study examined the frequency of college student’s yoga practice over the past year as a moderator of childhood maltreatment and PTSD symptoms in the past 30 days. Participants: Using a sample of 177 college students from a southern university. Methods: Participants competed an online survey in exchange for extra credit or entry into a gift card raffle. Results: Moderation analysis indicated that a more frequent yoga practice buffered the relationship between maltreatment and PTSD symptoms. Conclusion: Clinicians working with college students with a history of maltreatment are encouraged to make referrals to yoga classes. Universities are encouraged to adopt trauma-sensitive yoga programs.
... The probable reason for this is due profitable firms tend to establish a trade-off between the sustainability practices, that is, successfully, value creation and their cost may be rewarded earnings in terms of price of the share, that is, decrease their profitability as supported by EMH. This inverted U-shaped Effect size ≥ 0.005 is small, ≥0.01 is medium, and ≥0.025 is large (Kenny, 2021;Aguinis et al., 2005). Source: Authors' calculation. ...
Article
The purpose of this study is to theoretically and empirically extend the debate of the curvilinear linkage between corporate sustainability performance and its reporting practices (CSPR) and corporate financial performance (CFP) over its linearity assumption. The study focused on the financial and non‐financial metrics of the top global energy firms from 2006 to 2018 to accomplish this objective. It employed an estimated generalized least square method on the balanced panel of 3211 firm‐year observations. The findings assert the existence of a curvilinear relationship by spurning the linearity assumption. Further, results revealed a significant inverted U‐shaped relationship between CSPR and CFP. In addition to this, the investigation reveals that this relationship exists with the environmental and social attributes of CSPR. While the governance attribute was initially insignificant, however, it also exhibits a significant inverted‐U relationship after interacting with earnings. As a result, it adds to the existing literature by identifying earnings as a significant moderator in explaining the curvilinear relationship between CSPR and CFP. The inverted U‐shaped relationship may assist top management in developing a sustainable social and environmental policy based on a reactive strategy and help in formulating strategies to balance the value‐cost trade‐off for sustainable development.
... The average effect size of moderate tests published in major journals was only0.094 (Aguinis et al., 2005), so the current effect at the within-group level was medium. In addition, at the between-group level, the interaction between teacher-perceived principal leadership and teaching experience on teacher collaboration (β = −1.781, ...
Article
Full-text available
Teacher self-efficacy is one of the most critical factors influencing Students’ learning outcomes. Studies have shown that teacher-perceived principal leadership, teacher collaboration, and teaching experience are the critical factor that affects teacher self-efficacy. However, little is known about the mechanisms behind this relationship. This study examined whether teacher collaboration would mediate the relationship between teacher-perceived principal leadership and teacher self-efficacy, and the moderating role of teaching experience in the mediating process. With an analysis of a dataset from 14,121 middle school teachers in China, this study first testified to the positive role that teacher-perceived principal leadership played in teacher self-efficacy. Furthermore, it revealed that teacher collaboration mediates this relationship and the mediated path was moderated by teaching experience. Finally, it also indicated that the threshold of teaching experience linking the teacher-perceived leadership with teacher self-efficacy was approximately in the third year, and their relationship was stronger when teaching experience was below the threshold. This study highlighted the mediating and moderating mechanisms linking the teacher-perceived principal leadership and teacher self-efficacy, which has important theoretical and practical implications for intervention and enhancement of teacher self-efficacy.
... Second, the simple main effect of an old subjective age (.22) was not quantitatively smaller than the PTSD-subjective age main effect (.21). This issue is important, as in ordinal interactions, both the interaction and the simple effects are typically smaller than the main effects (Aguinis et al., 2005); unless however, as in the current case, one of the simple main effects is zero (Maxwell et al., 2017). Third, qualitatively, the simple main effects were revealing, the entire allostatic load effect, i.e., PTSD linking with detrimental health, only occurred under an old subjective age (McEwen, 1998). ...
Chapter
This closing chapter discusses the major advances in theory, research, and practice to show that the field of subjective views of aging (VoA) has indeed reached a qualitatively new developmental stage. At the theoretical level there is an increasing consensus that a lifespan developmental perspective may be most appropriate to study VoA across the adult years and into late life. This perspective can serve as a unifying framework with important implications for the integration of diverse literatures and increased methodological diversity and sophistication. Specifically, the impact of greater methodological diversity and sophistication is seen at the level of empirical research, including the greater diversity in study designs, the emerging focus on multilevel investigations (e.g., the concomitant study of biological, psychological, and social processes), and the translation into areas of intervention and prevention. All these advances bode well for the future of the field of VoA research and lay the foundation for promising future directions.
... It is important to note that effect sizes are reported in f 2 which is a common measure of interpreting effect sizes in tests of moderation (Aiken and West, 1991). Although the reported effect sizes are interpreted using Cohen's (1988) cutoffs for small, medium, and large effect sizes, Aguinis et al. (2005) note that effect sizes in tests of moderation tend to be conservative, averaging 0.009. Hence, Kenny (2018) posits that a more realistic standard for interpreting effect sizes in tests of moderation may be suitable − 0.005, 0.01, and 0.025 for small, medium, and large effects, respectively. ...
... Cohen's f 2 = .01). However, this is not surprising given that an interaction term must explain unique variance above and beyond both main effects of the independent variables, as well as numerous covariates (Aguinis et al., 2005;Aiken et al., 1991;McClelland & Judd, 1993). ...
Thesis
Youth antisocial behavior (AB; lying, aggression, rule-breaking) is a major public health concern due to its high prevalence and harmful consequences. Recent research has suggested that youth with AB are a heterogeneous group, which may undermine intervention success. For instance, elevated callous-unemotional (CU) traits are associated with more severe and persistent AB. Moreover, CU traits are a downward extension of psychopathic traits, and are a risk factor for adult psychopathy. Previous work suggests that the combination of AB and elevated CU traits may be etiologically distinct from AB alone. However, previous research has often been limited by the use of case-control designs in highly specialized populations, at severe levels of both AB and CU traits (e.g., adjudicated, clinical or criminal). This dissertation is comprised of three studies that examine developmental trajectories and neurocognitive deficits of AB versus CU traits, in community populations, across varying levels of AB and CU traits. To better understand developmental precursors of CU traits, Study 1 examines associations among parental psychopathic traits, parenting practices, and offspring CU traits in adolescence, using a genetically-informed design. Parental interpersonal-affective psychopathic traits were associated with adolescent CU traits and parenting (increased conflict, reduced involvement). Moreover, increased conflict and reduced involvement partially explained associations between parental interpersonal-affective traits and adolescent CU traits. Finally, using a twin difference design, we confirmed that adolescent CU traits were significantly impacted by non-shared environmental parenting influences (increased conflict, reduced involvement). Study 2 identifies neurocognitive deficits associated with the combination of AB and CU traits, in contrast to AB alone. Neither AB, nor CU traits alone, were associated with cognitive functioning when accounting for demographic factors. However, AB and CU traits interacted to predict reaction time variability. At low levels of CU traits, AB was associated with higher reaction time variability (traditionally thought to reflect worse sustained attention). At high levels of CU traits, antisocial behavior was associated lower reaction time variability (thought to reflect better sustained attention). Finally, Study 3 examines patterns of neural network connectivity underlying psychopathic traits in young adulthood using a person-specific approach and determines whether specific features of psychopathy are characterized by distinct network features. There was significant heterogeneity in neural networks of participants, which were characterized by person-specific connections and no common connections across the sample. Psychopathic traits, particularly affective traits, were associated with connection density between the default mode network and central executive network, such that greater density was associated with elevated psychopathic traits. The general discussion chapter of this dissertation highlights the implications of this research for intervention approaches, empirical considerations, and future directions.
... f 2 effect sizes of 0.02, 0.15, and 0.35 can be considered small, medium, and large, respectively(Cohen, 1988). However, when interpreting the interaction term's impact, these cutoffs result overly conservative and are commonly replaced by f 2 values of 0.005, 0.01, and 0.025(Aguinis et al., 2005;Kenny, 2018). ...
Article
Full-text available
Existing literature indicates that parenting styles affect the development of cyber aggression in offspring differently, depending on the gender of children. The present study investigates whether mothers’ and fathers’ parenting styles show similar gender differences in their associations with a new form of dating violence, i.e., cyber dating abuse (CDA). The limited evidence on the issue focuses on the relation that each parenting style has with CDA perpetration, without considering CDA victimization and the joint effects of fathers’ and mothers’ parenting styles. The present study contributes to the research on gender differences in parenting by examining whether young adults’ perceptions of maternal and paternal parenting styles during childhood were independently and/or jointly related to their perpetrated and suffered CDA and whether these relations differed across young adults’ gender. In total, 351 young adults (50.7% men), age between 18 and 35 years and having a romantic relationship, completed online self-reports of the variables of interest that include a bidimensional measure of perpetrated/suffered CDA that assess aggression and control. Results showed that maternal authoritarian parenting was uniquely and positively associated to their children’s perpetration and victimization of cyber dating control, whereas maternal permissive parenting was uniquely and positively related to their children’s perpetration of cyber dating aggression and victimization of cyber dating control. For daughters, these associations were stronger when the father’s style was similar to the mother’s one or when a maternal authoritarian style combined with a paternal permissive style, thus indicating that the two parents’ parenting styles interact in relating to their daughters’ CDA.
... In this regard, a total of 7-10 predictors were expected to be inserted into the anticipated regression models. According to previous published studies (e.g., Aguinis et al., 2005), a small effect size (f 2 = 0.02) was more frequently observed when evaluating the moderating effects in multivariate regression. Therefore, to achieve a 95% statistical power, we estimated that a minimum of 1100-1200 adolescents would be sufficient to make significant statistical inferences (Cohen, 1988). ...
Article
Full-text available
Anchored in the socio-ecological framework, the current study examined the association of teacher autonomy support with emotional-behavioral functioning profiles using a person-centered approach and investigated whether growth mindset and adolescents’ gender would moderate this association. To achieve these research objectives, this study involved 1741 adolescents (54.1% girls; M age = 12.62; SD = 1.50) who were uniformly instructed to fill in a set of self-report questionnaires. Results based on latent profile analysis revealed four emotional-behavioral functioning profiles: primarily externalizing (6.2%), comorbid (32.9%), well-adjusted (53.7%), and high-risk (7.2%). Adolescents with high teacher autonomy support were more likely to be group members of the well-adjusted profile than the remaining three emotional-behavioral functioning profiles. Moreover, interaction analyses demonstrated that girls benefited more when teacher autonomy support and growth mindset were congruently high, whereas boys did not. The current findings suggest that teachers should be equipped with sufficient skills and training to maintain an autonomy-supportive classroom climate. Meanwhile, growth mindset intervention may develop into an integral part of the school’s activities to facilitate adolescents’ optimal emotional-behavioral functions, but distinctly gendered pathways for these activities should be carefully considered.
Article
The measurement and communication of the effect size of an independent variable on a dependent variable is critical to effective statistical analysis in the Social Sciences. We develop ideas about how to extend traditional methods of evaluating relationships in multivariate models to explain and illustrate the statistical power of a focal independent variable. Even with a growing acceptance of the need to report effect sizes, scholars in the management community have few well-established protocols or guidelines for reporting effect sizes. In this editorial essay, we: (1) review the necessity of reporting effect sizes; (2) discuss commonly used measures of effect size and accepted cut-offs for large, medium, and small effect sizes; (3) recommend standards for reporting effect sizes via verbal descriptions and graphical presentations; and (4) present best practice examples of reporting and discussing effect size. In summary, we provide guidance for authors on how to report and interpret effect sizes, advocating for rigor and completeness in statistical analysis.
Thesis
Full-text available
In recent research, associations between low Openness and conservative or right-wing populist politics are often found. Threatening situations of one's own ingroup were also linked to negative attitudes towards outgroups and right-wing populism was associated with the subjective feeling of the threat from outside. In this study these aspects are examined together. Specifically, it should be shown whether the personality trait Openness to Experience influences and moderates the subjective understanding of a situation as a threat and subsequently also leads to a higher approval of right-wing populist values. The sample consisting of 225 participants was analyzed using a moderation analysis (PROCESS by Andrew Hayes). The two text snippets acted as the threat and control condition (independent variable), in which a text was presented on the future increase or constant development of migration in Austria. These were examined regarding to their impact on the dependent variables collective angst, right-wing populist attitudes (populism, exclusionism) and the propensity to vote (PTV) for the Freedom Party Austria (FPÖ), while Openness was used as a potential moderator. According to the results, Openness influences and increases the impact of a threat on populist attitudes as well as collective fear, but the interaction does not lead to higher values in exclusionism towards migrants and the likelihood of voting for a right-wing populist party (FPÖ). Nevertheless, the ideological, exclusionist - dimension of right-wing populism can be predicted by low Openness. Based on the Integrated Threat Theory the higher values in populism are interpreted as a group reaction, that stems from the threat towards one’s ingroup, while Openness moderates this relationship. The moderation is explained by Openness’ influence whether something is classified as threatening.
Article
Displaying enthusiasm (an emotional manifestation of passion) is a common practice for entrepreneurs to attract crowdfunding. However, we propose that funders may attribute an entrepreneur’s displayed enthusiasm to impression management motives, which can in turn reduce their funding intentions. Moreover, this negative pathway is more likely to occur when the entrepreneur is perceived to have lower domain expertise. We found consistent support for these hypotheses from a survey and an experiment. Our findings suggest that displaying enthusiasm may not always be effective for entrepreneurs because there are both positive and negative pathways underlying the influence of displayed enthusiasm on funders.
Article
Provide data on the five characteristics of emotional disturbance (ED). For 503 students with ED and 2016 without disabilities, teachers rated the characteristics (Inability to Learn; Relationship Problems; Inappropriate Behavior; Unhappiness or Depression; Physical Symptoms or Fears), plus Socially Maladjusted. We applied a 2 (ED, without disabilities) × 2 (female, male) × 3 (elementary, middle, high school) covariance analysis, with follow‐up comparisons. Students with ED showed greater problems than students without disabilities on all five characteristics, and Socially Maladjusted. On Inability to Learn, among students with ED genders did not differ at elementary but males had greater problems at middle school. On Inappropriate Behavior and Physical Symptoms or Fears, students with ED varied across school levels but students without disabilities did not. All five characteristics discriminated students with ED from those without disabilities. Differences between genders and school levels varied across characteristics. On all five IDEA characteristics of emotional disturbance (ED), students with ED show significantly more serious problems than their peers with no disabilities. Assessment of all five characteristics of ED can help the multidisciplinary team determine whether a student qualifies as ED. Assessment of the five characteristics can also suggest directions for school intervention. On all five IDEA characteristics of emotional disturbance (ED), students with ED show significantly more serious problems than their peers with no disabilities. Assessment of all five characteristics of ED can help the multidisciplinary team determine whether a student qualifies as ED. Assessment of the five characteristics can also suggest directions for school intervention.
Article
Organizations largely depend on their employees’ creativity to attain a competitive advantage. Drawing on Ability-Motivation-Opportunity (AMO) theory, this study examines whether employees’ voice behavior (promotive and prohibitive) can be harnessed to improve their creative performance. By exploring the mediating role of psychosocial prosperity and moderating effects of employees’ perception of their influence at work and their feelings of alienation, this study offers a unique model that enhances the literature on voice and creativity. Data collected from 285 Information Technology professionals in India reveals that both forms of voice lead to creative performance, and psychosocial prosperity mediates this positive relationship. This finding offers different insight for scholars as much of the voice literature expects prohibitive voice to yield negative results for the employee because of its associated risks. Also, employees’ perceived influence at work strengthens the positive effect of promotive voice on psychosocial prosperity, while alienation weakens the relationship between psychosocial prosperity and creativity performance. The study concludes by discussing the implications, limitations, and directions for future researchers.
Article
This study tests the positive effects of empowering leadership (ELSH) under boundary conditions in the hospitality industry. We propose the existence of an interactive process through which ELSH behaviors interact with employees’ personality type to condition their engagement, which in turn influences their extra-role service behavior. We use data from 294 employees and structural equation modeling. The results show that the interaction of ELSH with employees’ independent and interdependent personality is negatively related to their engagement. This decrease in engagement is then reflected in decreased extra-role service behaviors due to the positive relationship between engagement and extra-role service. These findings suggest that self-construal is a significant boundary condition capable of changing the positive relationship between ELSH and engagement to a negative one. Not considering this relationship when establishing a leadership strategy such as ELSH in the hospitality context could render efforts to achieve the goal of high-quality service ineffective.
Article
The purpose of this study was to determine whether perceived collective efficacy moderated the prospective relationship between school belonging and delinquency. Analyses were performed on a sample of 4048 youth (2020 boys, 1936 girls) from the Longitudinal Study of Australian Children (LSAC-K). Linear and negative binomial regression analyses performed with maximum likelihood (ML) and maximum likelihood with robust standard errors (MLR) estimators produced consistent results. Bootstrapped and normal theory analyses disclosed a significant interaction between school belonging and collective efficacy after age, sex, indigenous status, physical condition of dwelling, physical condition of surrounding housing, household income, weak parental monitoring, perceived peer delinquency, and prior delinquency were controlled. Further review of the significant interactive effect revealed that the increased levels of school belonging predicted decreased levels of future delinquency, but only when perceived collective efficacy was also elevated. These results support the presence of a small but significant conditional promotive effect.
Article
Analysis of the differential treatment effects across targeted subgroups and contexts is a critical objective in many evaluations because it delineates for whom and under what conditions particular programs, therapies or treatments are effective. Unfortunately, it is unclear how to plan efficient and effective evaluations that include these moderated effects when the design includes partial nesting (i.e., disparate grouping structures across treatment conditions). In this study, we develop statistical power formulas to identify requisite sample sizes and guide the planning of evaluations probing moderation under two-level partially nested designs. The results suggest that the power to detect moderation effects in partially nested designs is substantially influenced by sample size, moderation effect size, and moderator variance structure (i.e., varies within groups only or within and between groups). We implement the power formulas in the R-Shiny application PowerUpRShiny and demonstrate their use to plan evaluations.
Article
Personality researchers have posited multiple ways in which the relations between personality traits and life outcomes may be moderated by other traits, but there are well-known difficulties in reliable detection of such trait-by-trait interaction effects. Estimating the prevalence and magnitude base rates of trait-by-trait interactions would help to assess whether a given study is suited to detect interaction effects. We used the Life Outcomes of Personality Replication Project dataset to estimate the prevalence, nature, and magnitude of trait-by-trait interactions across 81 self-reported life outcomes ( n ≥ 1350 per outcome). Outcome samples were divided into two halves to examine the replicability of observed interaction effects using both traditional and machine learning indices. The study was adequately powered (1 − β ≥ .80) to detect the smallest interaction effects of interest (interactions accounting for a Δ R ² of approximately .01) for 78 of the 81 (96%) outcomes in each of the partitioned samples. Results showed that only 40 interactions (5.33% of the original 750 tests) showed evidence of strong replicability through robustness checks (i.e., demographic covariates, Tobit regression, and ordinal regression). Interactions were also uniformly small in magnitude. Future directions for research on trait-by-trait interactions are discussed.
Article
This study analyzes the link between a firm's digital reputation and performance and the conditions under which its orientation towards sustainable development can moderate this link. The manuscript deals with relevant topics such as the digital tools that support the implementation of the firm's sustainability strategy, concerning the firm's commitment to deploying Sustainable Development Goals (SDGs). Using a sample of firms from the Fortune 500 list from 2015 to 2019, the findings show that digital reputation positively impacts a firm's financial and non-financial performance. Furthermore, results reveal that breadth (the variety of SDG-related themes covered) and concentration (the distribution of non-financial disclosure among the SDGs) operate as moderators in the above relationship. On the other hand, depth (the total volume of the SDG-based information) appears not to be significant. Finally, this study enriches the debate by providing a new data operationalization process to measure the firm's commitment to the SDGs of the 2030 Agenda.
Article
Full-text available
Purpose The purpose of this paper, an empirical research, is to identify the psychological and functional barriers that result in e-waste recycling resistance. Design/methodology/approach The study is equipped with the theoretical lens of the innovation resistance theory. Households living in an Indian city were surveyed using a pre-validated questionnaire. Statistical analysis for the study was done with partial least squares – structural equation modeling. Findings The outcome of the survey exhibited that the significant factors contributing to e-waste recycling resistance are usage barrier, value barrier, risk barrier and tradition barrier. Practical implications The study offers implications for multiple stakeholders, which aid them in formulating strategies to overcome e-waste recycling resistance. Originality/value This research has remarkable importance as it is the pioneering study that extensively investigates the reasons for e-waste recycling resistance in an emerging economy. The study also empirically validates the moderating role of environmental awareness, age, gender and income in the relationship between barriers and resistance to e-waste recycling.
Chapter
Adverse life events, such as trauma or stress, along with subjective perceptions regarding the aging self, constitute two issues that influence late-life development. Yet, earlier literature paid less attention to the ways in which these aspects may intersect in old age. The current chapter focuses on what studies of trauma teach us about subjective views of aging (VoA). Two VoA (subjective age and subjective estimated time to death, SETtD) are reviewed in the context of diverse traumatic events that may occur across the life span. This literature review along with application of meta-analytical techniques, suggests that these VoA, in addition to measuring aspects of age identity, also measure a ratio of resources to stressors, either in the past/present (subjective age) or with regard to the future (e.g., SETtD). Namely, having more past resources than past stressors would reflect a younger subjective age, similarly, having more estimated future resources than estimated future stressors would reflect a longer SETtD. One implication of this resource/stress model of VoA is that the same young subjective evaluation reflecting the same resource-stress ratio, may stem from different patterns, e.g., high resources with slightly lower stress or from low resource levels coupled by even lower stress. Additional issues are also clarified by this conceptualization, along with unresolved issues awaiting future research that are discussed. This proposed theoretical outlook leads to novel theoretical and practical implications.
Article
Blockchain is a disruptive technology that is expected to revolutionize the world of trusted transactions. Through a combination of cryptographic techniques, a distributed, shared, and immutable ledger, consensus validation of transactions, and a financial audit trail, blockchain is poised to do for businesses what the Internet did for communication. With its promise of reducing cost, time, friction, and fraud in business transactions and ensuring trust, identity management, and reputation management, companies around the world are now contemplating their transition to blockchain versions of themselves. However, the cost of implementing such technology and its effect on the readiness of the organization to adopt blockchain has not been fully explored yet. This study examines the mediation and moderation roles of the perceived cost on the relationship between organization readiness and the intention to adopt blockchain. Data was collected from blockchain experts and Partial least squares structural equation modeling (PLS-SEM) was used as the analytical tool to test all of the framework hypotheses. To investigate the potential managerial implications of this topic, Importance-Performance Map Analysis (IPMA) was utilized. The findings reveal that perceived cost is not a mediator; rather, it moderates the relationship between the TRI (Technology Readiness Index) enablers and the TRI inhibitors with the intention to adopt blockchain. In terms of importance, the empirical data analysis through IPMA revealed that the enablers construct is the most important factor, while perceived cost has the highest performance on the intention to adopt blockchain. With this discovery, our findings are expected to aid decision-makers in prioritizing and improving the enabling aspects required for the successful adoption of blockchain technology.
Article
Although ethical leadership is thought to motivate employees to refrain from deviant behaviors that are harmful to the organization and its members, scholars have also found considerable variability in the relationship between ethical leadership and deviant subordinate behaviors beyond this general or main effect. Integrating theory on ethical leadership and work engagement, we develop and test a model that also considers the role of employee-leader value similarity in understanding employee interpersonal and organizational deviance. In two field studies employing multi-wave samples of leader-subordinate dyads, we demonstrate that value similarity moderates the effects of ethical leadership on subordinate deviance and does so via engagement. Implications for ethical leadership, employee engagement, and deviance literature are discussed.
Article
Full-text available
In recent years, multiple regression has been widely used in social sciences to analyze the moderating effect. However, this practice was found to have at least four weaknesses. First, the concept of moderation is artificially treated as interaction. Second, the role of the predictor X is confounded with that of the moderator Z. That is, the roles of the predictor and the moderator are statistically indistinguishable, or the moderation effect of Z equals that of X. Third, the assumption of homoscedasticity of error variances across different values of X and Z is often violated by data in social and behavioral sciences. Violating this assumption often results in an inflated Type Ⅱ error rate and a low power. Fourth, △R2 does not directly measure the effect of moderation as conceptually defined. That is, a measure that reflects the impact of Z on the relationship between X and Y (i.e., X→Y) should be used to quantify the moderating effect. Compared to multiple regression, the two-level regression model has many advantages in the analysis of moderating effect. First, the two-level regression model does not require the homoscedasticity assumption in moderation analysis. Second, the two-level regression model allows the regression coefficients of a dependent variable Y on predictor X (i.e., X→Y) are further regressed on moderator variables Z. Therefore, the two-level regression model permits estimating the percentage of variance of each regression coefficient that is due to moderator variables (i.e., the moderation effect size). The two-level regression model directly shows us to what extent a moderator explains the variance of the regression coefficient between the dependent variable and the predictor. At the present study, we propose a procedure to analyze the moderating effect based on the two-level regression model. The first step is to determine the moderating effect using the two-level regression model. If the variance of the error εi1 of the level 2 slope equation is statistically significant, the result of the two-level regression model and the corresponding effect size should be reported. Otherwise, go to the second step. In the second step, multiple regression was used to work out the moderating effect. If the Bayesian information criterion of the two-level regression model is smaller than that of the multiple regression, the result of the two-level regression model and the corresponding effect size should be reported. Otherwise, the result of the multiple regression and the corresponding effect size △R2 should be reported. We exemplify how to conduct the proposed procedure by using Mplus. It is noteworthy that, with this software, a two-level regression model could be built via a “trick” for 2-level model with single level data. The Mplus syntax is offered to facilitate the implementation of two-level regression model in analyzing moderated mediation effects. The program can be managed easily by empirical researchers. Directions for future study on two-level regression model are discussed at the end of the paper. First, if data contains outliers or heavy tails, robust methods of two-Level regression model should be adapted. Second, if the measurement error of the variables needs to be taken into account, two-level moderated latent variable model should be adapted. Third, two-level regression model could be used to analyze the mediated moderation model and moderated mediation model.
Article
Full-text available
This study, conducted in Singapore, where there are ongoing labor shortages, supports social exchange theory predictions that contingent workers engage in less organizational citizenship, expect less of their employers in their psychological contracts, and have lower affective commitment than regular employees, Contrary to expectations, the relationship between two attitudes-commitment and psychological contracts- and organizational citizenship was stronger for contingent workers than for regular employees, indicating that when contingent workers have positive attitudes about their relationship with an organization, they engage in organizational citizenship behavior. We discuss the implications of these unexpected results for theory and practice.
Article
Full-text available
Power analysis after study completion has been suggested to interpret study results. We present 3 methods of estimating power and discuss their limitations. We use simulation studies to show that estimated power can be biased, extremely variable, and severely bounded. We endorse the practice of computing power to detect a biologically meaningful difference as a tool for study planning but suggest that calculation of confidence intervals on the parameter of interest is the appropriate way to gauge the strength and biological meaning of study results.
Article
Full-text available
This study is based on a review of several papers on multiple regression (with an emphasis on moderated regression) that have recently been published in the Journal of Management and elsewhere. Independent contributions from each of these articles suggest six sets of questions and/or conclusions that might motivate future researchers in this area, and we call for research which integrates the questions into unified studies.
Article
Full-text available
Given the overwhelming research evidence showing the strong link between general cognitive ability (GCA) and job performance, it is not logically possible for industrial -organizational (I/O) psychologists to have a serious debate over whether GCA is important for job performance. However, even if none of this evidence existed in I/O psychology, research findings in differential psychology on the nature and correlates of GCA provide a sufficient basis for the conclusion that GCA is strongly related to job performance. In I/O psychology, the theoretical basis for the empirical evidence linking GCA and job performance is rarely presented, but is critical to understanding and acceptance of these findings. The theory explains the why behind the empirical findings. From the viewpoint of the kind of world we would like to live in - and would like to believe we live in - the research findings on GCA are not what most people would hope for and are not welcome. However, if we want to remain a science-based field, we cannot reject what we know to be true in favor of what we would like to be true.
Article
Full-text available
Claims that cognitive ability tests of the kind generally used in personnel selection are valid predictors of successful performance for jobs in all settings. This controversial stance is supported by analyses that recast findings of invalid tests as instances of Type I error. Ideally, if an employer has large enough samples, perfectly reliable tests, and an unrestricted range of ability in the applicant pool, the most widely used types of standardized tests should be valid in all job situations, and the notion of job-specific validity would no longer hold. The authors argue against previous reservations about the suitability of cognitive ability tests for employee selection that were made on the basis of their supposed limited applicability, their bias, and their ultimate contribution to workforce productivity. (56 ref) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Full-text available
Agrees with A. H. Eagly's (see record 1995-21141-001) contention that the use of easily understood metrics (binomial effects size display and the common language effect) are not entirely sufficient at showing a significant sex effect. The authors recommend the use of computer simulations as a tool for assessing the impact of sex differences. Results of a computer simulation regarding the effects of pyramid structure and initial performance ratings on limitations of the upward mobility of women in the workplace confirm Eagly's point that the effects of male–female differences are best determined not only by the magnitude of the effect but its consequences in natural settings. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Full-text available
A survey of all PhD programs in psychology in the US and Canada assessed the extent to which advances in statistics, measurement, and methodology have been incorporated into doctoral training. In all, 84% of the 222 departments responded. The statistical and methodological curriculum has advanced little in 20 yrs; measurement has experienced a substantial decline. Typical 1st-yr courses serve well only those students who undertake traditional laboratory research. Training in top-ranked schools differs little from that in other schools. New PhDs are judged to be competent to handle traditional techniques, but not newer and often more useful procedures, in their own research. Proposed remedies for these deficiencies include revamping the basic required quantitative and methodological curriculum, culling available training opportunities across campus, and training students in more informal settings, along with providing retraining opportunities for faculty. These strategies require attention to the human capital needs that support high-quality quantitative and methodological training and practice. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Treatment subjects (n = 173) received an explanation for an ongoing pay freeze. This explained the fairness of the implementation of the freeze and the necessity for it. The explanation mitigated the effect of the resultant economic harships on employees attitudes, turnover intentions, and perceptions of procedural justice.
Article
In the analysis of data it is often assumed that observations y1, y2, …, yn are independently normally distributed with constant variance and with expectations specified by a model linear in a set of parameters θ. In this paper we make the less restrictive assumption that such a normal, homoscedastic, linear model is appropriate after some suitable transformation has been applied to the y's. Inferences about the transformation and about the parameters of the linear model are made by computing the likelihood function and the relevant posterior distribution. The contributions of normality, homoscedasticity and additivity to the transformation are separated. The relation of the present methods to earlier procedures for finding transformations is discussed. The methods are illustrated with examples.
Article
Monte Carlo simulations were conducted to examine the degree to which the statistical power of moderated multiple regression (MMR) to detect the effects of a dichotomous moderator variable was affected by the main and interactive effects of (a) predictor variable range restriction, (b) total sample size, (c) sample sizes for 2 moderator variable-based subgroups, (d) predictor variable intercorrelation, and (e) magnitude of the moderating effect. Results showed that the main and interactive influences of these variables may have profound effects on power. Thus, future attempts to detect moderating effects with MMR should consider the power implications of both the main and interactive effects of the variables assessed in the present study. Otherwise, even moderating effects of substantial magnitude may go undetected.
Article
Various forms of score adjustment have been suggested and used when mean differences by gender, race, or ethnicity are found using preemployment tests. This article examines the rationales for score adjustment and describes and compares different forms of score adjustment, including within-group norming, bonus points, separate cutoffs, and banding. It reviews the legal environment for personnel selection and the circumstances leading to the passage of the Civil Rights Act of 1991. It examines score adjustment in the use of cognitive ability tests, personality inventories, interest inventories, scored biographical data, and physical ability tests and outlines the implications for testing practice of various interpretations of the Civil Rights Act of 1991.
Article
In 3 studies, the author investigated individuals' attitudes toward corporate drug-testing Subjects in a laboratory experiment held favorable attitudes toward (a) punitive drug-testing programs for employees in safety-sensitive occupations and (b) less punitive drug-testing programs for employees in less safety-sensitive occupations. However, in a correlational field study, employees in safety-sensitive positions held more negative attitudes toward punitive programs than did drug-tested individuals in less safety-sensitive positions. In an inductive investigation of fairness determinants, tested and nontested employees invoked different justice rules when assessing the fairness of highly punitive drug-testing programs. Implications for research and practice are discussed.
Article
In this study, we extended agency-based research by examining the role of risk in the structure of managerial compensation and its relationship to organization performance. Our results suggest that organizations facing higher risk do not place greater emphasis on short-term incentives than other organizations - rather, they place less emphasis on them. Also, higher-risk firms that relied on incentive pay exhibited poorer performance than higher-risk firms that did not emphasize incentive pay.
Article
A letter from the editor is presented which discusses the role of meta-analysis and replication research in the articles submitted to the periodical for review. The author points out that the journal uses the idea of articles having an important contribution to the field of management as a basis for review. This leads many of the articles to contain information on relatively new ideas, even though some of those ideas contain information of little importance. For this reason, the periodical accepts articles containing replication research and meta-analysis.
Article
A comparative analysis of professionals' use of individual self-managing activities in functional and cross-functional units found that individual self-management was beneficial for effectiveness in functional units but not in cross-functional units. The study also explored the effects of interactions of individual self-management and unit type (functional or cross-functional) on team members' overall levels of job satisfaction and perceptions of bureaucratic obstacles. Results suggest a need for a contingency model of self-management and a need to pursue the multidimensionality of the self-management construct.
Article
A new asymptotic formula for estimating the sampling variance of a correlation coefficient corrected for unreliability and range restriction was proposed. A Monte Carlo assessment of the new sampling variance formula has resulted in the following conclusions. First, the formula-based (analytical) sampling variances were very close to the empirically derived sampling variances based on 5,000 replications. Second, the sampling variance formula was quite robust against committing Type I errors. Third, the statistical power was low to moderate in distinguishing between two unattenuated and unrestricted population correlations. Fourth, the new formula produced smaller sampling variances; was closer to nominal alpha levels; and was more powerful when sample size increased, when the population correlation coefficient increased, when range restriction was less severe, and when both the criterion and predictor reliabilities increased.
Article
Standard errors of estimators that are functions of correlation coefficients are shown to be quite dif ferent in magnitude than standard errors of the ini tial correlations. A general large-sample methodo logy, based upon Taylor series expansions and asymptotic correlational results, is developed for the computation of such standard errors. Three ex emplary analyses are conducted on a correction for attenuation, a correction for range restriction, and an indirect effect in path analysis. Derived for mulae are consistent with several previously pro posed estimators and provide excellent approxima tions to the standard errors obtained in computer simulations, even for moderate sample size (n = 100). It is shown that functions of correlations can be considerably more variable than product-mo ment correlations. Additionally, appropriate hy pothesis tests are derived for these corrected coeffi cients and the indirect effect. It is shown that in the range restriction situation, the appropriate hypothe sis test based on the corrected coefficient is asymp totically more powerful than the test utilizing the uncorrected coefficient. Bias is also discussed as a by-product of the methodology.
Article
A revised and improved version of Aguinis, Pierce, and Stone-Romero's (1994) program for estimating the statistical power of moderated multiple regression to detect dichotomous moderator variables is described. The Quick BASIC program runs on IBM and IBM-compatible personal computers and estimates power based on user-provided values for (a) total sample size, (b) sample sizes across the two moderator-based subgroups, (c) correlation coefficients between the predictor and criterion for each of the two moderator-based subgroups, (d) correlation coefficient between the predictor and hypothesized moderator, and (e) sample and population standard deviations for the predictor. Program-generated power estimates for typical research situations in education, psychology, and management indicate that hypothesis tests of moderating effects are typically conducted at insufficient levels of statistical power.
Article
As part of their investigation of the relation between reliability of measures and statistical power, Nicewander and Price (1983) examined the situation in which true score regressions are homogeneous across treatments. They derived an equation indicating that the measure, X or Y, yielding the greater power depends on the reliabilities (pXX'. and pYY', respectively) and the squared linear correlation between true scores for X and Y (pT(X)T(Y)2). Typically, however, researchers cannot compute a direct estimate of pT(X)T(Y)2 The authors eliminate this problem by (a) pointing out situations in which the value of pT(X)T(Y)2 is either irrelevant or 1.0 and (b) demonstrating that their equation otherwise can be expressed in terms of pXX' and pXY only.
Article
A QuickBASIC program for estimating the statistical power to detect the effects of dichotomous moderator variables using moderated multiple regression (MMR) is available. The program runs on IBM and IBM-compatible personal computers and estimates power based on specific values for (a) total sample size, (b) sample sizes across the two categories of the hypothesized moderator, and (c) correlation coefficients between predictor and criterion scores for each of the two moderator-based subgroups. The compiled run time and source code versions of the program can be obtained from the first author.
Article
Homogeneity of within-subgroup error (residual) variance is a necessary statistical assumption for the appropriate use of moderated multiple regression (MMR) for assessing the effects of categorical moderator variables (e.g., ethnicity, gender). We provide a conceptual review of the homogeneity of error variance assumption in the context of MMR analyses. First, we clarify issues pertaining to the violation of the homogeneity of error variance assumption and differentiate it from the homoscedasticity assumption. Second, we delineate the implications of violating the homogeneity of error variance assumption for organizational theory and practice. Finally, we critically review solutions recently proposed to mitigate the detrimental effects of violating the homogeneity of error variance assumption on conclusions regarding the effects of categorical moderator variables.
Article
Monte Carlo simulation procedures were used to assess the power of moderated multiple regression (MMR) to detect the effects of a dichotomous moderator variable under conditions of: (1) between- group differences in within-group relationships between two variables (i.e., |ρXY(1) -ρXY(2) |= .20, .40, .60); (2) different combined sample sizes for the two groups (N1+ N2 = NT = 30, 60, 90, 180, 300); and (3) differing proportions of cases (P-i) in the two groups (i.e., P 1 = .10, .30, .50). Results showed that, consistent with our a priori predictions, the power of MMR increased as: (1) total sample size (NT) increased; (2) the difference between within-group correlation coefficients increased; and ( 3) the difference between the proportion of cases in each group decreased. Moreover, the simulation showed that these three variables had interactive effects on power. The major implication of our findings is that in cases where tests of moderating effects are conducted with MMR and the proportion of cases in each group differs greatly, inferences of no moderating effect may be erroneous: Such inferences may be the result of low statistical power rather than the absence of a moderating effect.
Moderator variables (moderators) are of considerable interest to researchers in various academic disciplines (e.g. human resources management, industrial and organizational psychology, management, organizational behavior, and organizational theory) who study phenomena involving the interactive effects of two or more independent variables. Several comprehensive reviews of the literature on moderators have appeared in the past three decades (e.g. Stone, 1988; Zedeck, 1971). Since the latest of these reviews, a large number of papers have been published on moderator-related issues. Unfortunately, however, there is no relatively comprehensive, up-to-date review of this literature. Thus, the purpose of this article is to provide such a review. Among the topics considered in it are conceptual definitions of moderators, prior reviews of the literature on moderators, major strategies for detecting moderators, and strategies for increasing statistical power in studies of moderators.
Article
Homogeneity of within-subgroup error variance is a necessary condition for using multiple regression to estimate moderating effects of categorical variables. A 12-year review of Academy of Management Journal, Journal of Applied Psychology, and Personnel Psychology indicates that the assumption is violated in 40% to 60% of cases. The authors reanalyze published research to illustrate how violating the assumption may change substantive conclusions. To remedy this situation, they develop and present a computer program (i.e., ALTMMR) that (a) assesses whether a data set suffers from heterogeneity of error variance and (b) computes alternative inferential statistics to the traditional multiple regression F test when heterogeneity exists. ALTMMR, which can also be used as a teaching tool, was written in Java and is executable using an Internet Web browser or as a standalone application.
Article
This study investigated the informal networks of white and minority managers. Minority managers had more racially heterogeneous and fewer intimate network relationships. Within the minority group, differences in advancement potential were associated with different network configurations: high-potential individuals balanced same- and cross-race contacts; others had networks dominated by ties to whites. High-potential minorities also had more contacts outside their groups, fewer high-status ties, and less overlap between their social and instrumental circles. Relative to whites, minority managers viewed similar network characteristics as providing less access to career benefits.
Book
This study investigated 3 broad classes of individual-differences variables (job-search motives, competencies, and constraints) as predictors of job-search intensity among 292 unemployed job seekers. Also assessed was the relationship between job-search intensity and reemployment success in a longitudinal context. Results show significant relationships between the predictors employment commitment, financial hardship, job-search self-efficacy, and motivation control and the outcome job-search intensity. Support was not found for a relationship between perceived job-search constraints and job-search intensity. Motivation control was highlighted as the only lagged predictor of job-search intensity over time for those who were continuously unemployed. Job-search intensity predicted Time 2 reemployment status for the sample as a whole, but not reemployment quality for those who found jobs over the study's duration. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Investigators in numerous organization studies disciplines are concerned about the low statistical power of moderated multiple regression (MMR) to detect effects of categorical moderator variables. The authors provide a theoretical approxima- tion to the power of MMR. The theoretical result confirms, synthesizes, and ex- tends previous Monte Carlo research on factors that affect the power of MMR tests of categorical moderator variables and the low power of MMR in typical research situations. The authors develop and describe a computer program, which is avail- able on the Internet, that allows researchers to approximate the power of MMR to detect the effects of categorical moderator variables given user-input information (e.g., sample size, reliability of measurement). The approximation also allows in- vestigators to determine the effects of violating certain assumptions required for MMR. Given the typically low power of MMR, researchers are encouraged to use the computer program to approximate power while planning their research design and methodology.
Article
Due to the increasing importance of moderating (i.e., interaction) effects, the use of moderated multiple regression (MMR) has become pervasive in numerous management specialties such as organizational behavior, human resources management, and strategy, to name a few. Despite its popularity, recent research on the MMR approach to moderator variable detection has identified several factors that reduce statistical power below acceptable levels and, consequently, lead researchers to erroneously dismiss theoretical models that include moderated relationships. The present article (1) briefly describes MMR, (2) reviews factors that affect the statistical power of hypothesis tests conducted using this technique, (3) proposes solutions to low power situations, and (4) discusses areas and problems related to MMR that are in need of further investigation.
Article
In moderated regression analysis with both a continuous predictor and nominal-level (group membership) variables, there are conditions in which the hypothesis of equal slopes of the regression of Y onto X across groups is equivalent to the hypothesis of equality of X– Y correlations across groups. This research uses those conditions to investgate the impact of heterogeneity of error variance on the power accuracy of the F test for equality of regression slopes. The results show that even when sample sizes are equal, the test is not robust and, under unequal sample sizes, the pattern of excessively high or excessively low rejection rates can be severe. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Investigated, in 3 studies, individuals' attitudes toward corporate drug-testing programs. 75 undergraduates in a laboratory experiment held favorable attitudes toward (1) punitive drug-testing programs for employees in safety-sensitive occupations and (2) less punitive drug-testing programs for employees in less safety-sensitive occupations. However, in a correlational field study, 108 drug-tested employees in safety-sensitive positions held more negative attitudes toward punitive drug-testing programs than did drug-tested individuals in less safety-sensitive positions. In an inductive investigation of fairness determinants, 664 tested and nontested employees invoked different justice rules when assessing the fairness of highly punitive drug-testing programs. Implications for research and practice are discussed. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
As women are encouraged to enter nontraditional occupations, it is important to identify factors that may promote a successful transition. Data from carpenter apprentices and instructors were analyzed to compare men and women. In some aspects, based on performance and satisfaction with the apprentice program, the union, and carpentry work, the transition into carpentry is as successful for women as for men. Women give themselves a higher probability of completing the program than do men. Problem areas are evident, however. Women are employed in construction less than men, and their male co-workers have negative attitudes toward affirmative action. In terms of factors associated with success, differences between men and women emphasized co-worker acceptance, fairness in job assignments, age, and realistic expectations. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
the purpose of personality assessment is "the obtaining and evaluating of information regarding individual differences" / although the reasons for obtaining and evaluating such information are diverse, the prediction of useful criteria is a major one / the impetus for much of the work in the field of personality assessment has been the quest for large predictive validity coefficients prediction models (the bivariate linear model, multivariate extension, interactive models) / description and evaluation of some interactive models (personality consistency, differential predictability, student characteristics and instructional techniques, empirical evaluation, what went wrong) / implications for applied psychology (the importance of theory, explanation vs prediction, the virtues of simplicity) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Defines and categorizes alternative concepts of "moderator" variables categorized in terms of whether they lead to differential validity or predictability, or involve moderated regression techniques. The dissimilarity of results provided by the 3 approaches is discussed in terms of the type of variable (qualitative vs. Quantitative) examined as a moderator and in terms of statistical and methodological problems. The major problems of the operation and identification of moderator variables also are discussed. Utility of the moderator variable concept is examined. (58 ref.) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Examined several causes for discrepant findings in the literature related to sex differences in job outcome preferences. 648 college graduates newly hired into entry-level business jobs over a 9-yr period rated job characteristics comprising 3 job outcome dimensions: (a) long-term career objectives, (b) working environment and interpersonal relationships, and (c) intrinsic job aspects. The possibility that the area of professional training could account for sex differences in job outcome preferences was explored, controlling for age, education, organizational level, and occupational category. Although professional training area did have a significant effect on job outcome preferences, sex differences persisted, with females giving significantly less emphasis to career objectives and significantly more emphasis to work environment and interpersonal job aspects than males. Analyses of trends showed a convergence of female preferences toward those of males on the 2 dimensions in which sex differences were found. Efforts to predict turnover from job outcome preferences suggested that females with a relatively high career orientation were less likely than males or other females to leave the organization. (23 ref) (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
In a randomized field experiment involving 173 salaried employees, treatment Ss received an explanation for an ongoing pay freeze. This explained the fairness of the decision process leading to the freeze and the fairness of the implementation of the freeze. The explanation mitigated the effect of the resultant economic hardship on employee attitudes, turnover intentions, and perceptions of procedural justice. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
The long-term impact of studies of statistical power is investigated using J. Cohen's (1962) pioneering work as an example. We argue that the impact is nil; the power of studies in the same journal that Cohen reviewed (now the Journal of Abnormal Psychology) has not increased over the past 24 years. In 1960 the median power (i.e., the probability that a significant result will be obtained if there is a true effect) was .46 for a medium size effect, whereas in 1984 it was only .37. The decline of power is a result of alpha-adjusted procedures. Low power seems to go unnoticed: only 2 out of 64 experiments mentioned power, and it was never estimated. Nonsignificance was generally interpreted as confirmation of the null hypothesis (if this was the research hypothesis), although the median power was as low as .25 in these cases. We discuss reasons for the ongoing neglect of power. (PsycINFO Database Record (c) 2012 APA, all rights reserved)
Article
Monte Carlo simulations were conducted to examine the degree to which the statistical power of moderated multiple regression (MMR) to detect the effects of a dichotomous moderator variable was affected by the main and interactive effects of (a) predictor variable range restriction, (b) total sample size, (c) sample sizes for 2 moderator variable-based subgroups, (d) predictor variable intercorrelation, and (e) magnitude of the moderating effect. Results showed that the main and interactive influences of these variables may have profound effects on power. Thus, future attempts to detect moderating effects with MMR should consider the power implications of both the main and interactive effects of the variables assessed in the present study. Otherwise, even moderating effects of substantial magnitude may go undetected. (PsycINFO Database Record (c) 2012 APA, all rights reserved)