Andrew F. Hayes's research while affiliated with The University of Calgary and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (80)
Mediation analysis is widely used to test and inform theory and debate about the mechanism(s) by which causal effects operate, quantitatively operationalized as an indirect effect in a mediation model. Most effects operate through multiple mechanisms simultaneously, and a mediation model is likely to be more realistic when it is specified to captur...
This work provides a conceptual introduction to mediation, moderation, and conditional process analysis in psychological research. We discuss the concepts of direct effect, indirect effect, total effect, conditional effect, conditional direct effect, conditional indirect effect, and the index of moderated mediation index, while providing our perspe...
Cronbach’s alpha (α) is a widely-used measure of reliability used to quantify the amount of random measurement error that exists in a sum score or average generated by a multi-item measurement scale. Yet methodologists have warned that α is not an optimal measure of reliability relative to its more general form, McDonald’s omega ( ω). Among other r...
Research in communication and other social science disciplines that relies on measuring each member of a dyad on putative causes and effects can require complex analyses to illuminate how members of the dyad influence one another. Dyadic mediation analysis is a branch of mediation analysis that focuses on establishing the mechanism(s) by which mutu...
Behavioral scientists use mediation analysis to understand the mechanism(s) by which an effect operates and moderation analysis to understand the contingencies or boundary conditions of effects. Yet how effects operate (i.e., the mechanism at work) and their boundary conditions (when they occur) are not necessarily independent, though they are ofte...
Mediation of X’s effect on Y through a mediator M is moderated if the indirect effect of X depends on a fourth variable. Hayes [(2015). An index and test of linear moderated mediation. Multivariate Behavioral Research, 50, 1–22. doi:10.1080/00273171.2014.962683] introduced an approach to testing a moderated mediation hypothesis based on an index of...
Marketing, consumer, and organizational behavior researchers interested in studying the mechanisms by which effects operate and the conditions that enhance or inhibit such effects often rely on statistical mediation and conditional process analysis (also known as the analysis of “moderated mediation”). Model estimation is typically undertaken with...
Article is open access through 2017: http://www.tandfonline.com/doi/full/10.1080/19312458.2016.1271116
Empirical communication scholars and scientists in other fields regularly use regression models to test moderation hypotheses. When the independent variable X and moderator M are dichotomous or continuous, the practice of testing a linear moderat...
There have been numerous treatments in the clinical research literature about various design, analysis, and interpretation considerations when testing hypotheses about mechanisms and contingencies of effects, popularly known as mediation and moderation analysis. In this paper we address the practice of mediation and moderation analysis using linear...
Researchers interested in testing mediation often use designs where participants are measured on a dependent variable Y and a mediator M in both of 2 different circumstances. The dominant approach to assessing mediation in such a design, proposed by Judd, Kenny, and McClelland (2001), relies on a series of hypothesis tests about components of the m...
I describe a test of linear moderated mediation in path analysis based on an interval estimate of the parameter of a function linking the indirect effect to values of a moderator—a parameter that I call the index of moderated mediation. This test can be used for models that integrate moderation and mediation in which the relationship between the in...
High negative emotionality (NE), low positive emotionality (PE), and low effortful control (EC) are each associated with elevated depressive symptoms and each moderates the effects of the others. However, those 2-way interactions consistently emerge only at some levels of the third dimension. This NE x PE x EC interaction yields a “best two out of...
Research on the impersonal impact hypothesis suggests that news (especially print) coverage of health and safety risks primarily influences perceptions of risk as a societal issue, and not perceptions of personal risk. The authors propose that the impersonal impact of news-impact primarily on concerns about social-level risks-will mediate effects o...
Virtually all discussions and applications of statistical mediation analysis have been based on the condition that the independent variable is dichotomous or continuous, even though investigators frequently are interested in testing mediation hypotheses involving a multicategorical independent variable (such as two or more experimental conditions r...
A content analysis of 2 years of Psychological Science articles reveals inconsistencies in how researchers make inferences about indirect effects when conducting a statistical mediation analysis. In this study, we examined the frequency with which popularly used tests disagree, whether the method an investigator uses makes a difference in the concl...
We test an uninvestigated proposition from spiral of silence theory that fear of social isolation (FSI) prompts people to seek out information about the climate of public opinion. Taking a trait-based individual difference perspective, the authors develop and validate a measure of FSI that is less likely to produce the interpretational problems tha...
This article tests the cross-cultural generality of one tenet of spiral of silence theory using an individual difference approach. We argue that the spiral of silence phenomenon is, in part, a manifestation of individual differences in stable personality traits that can be measured universally regardless of country or context -specifically, fear of...
We explored whether contact with business-related social ties would buffer entrepreneurs against the potentially deleterious effects of economic stress. Our proposed stress-buffering model builds on the premise that social ties with similar others can serve as both a source of valuable information and a source of empathic support. Findings from a s...
Little is known about the effect of craving on smoking abstinence among cardiac patients who smoked prior to admission and the mechanisms that might facilitate success in smoking cessation after discharge from hospital. This study examined the mediating effect of self-efficacy on the relationship between craving and smoking abstinence and how this...
Prior research has shown that the proportion of news stories about violent crimes, car crashes, and other unintended injuries that mention the possible contributing role of alcohol is far lower than the actual proportion of alcohol-related crimes and unintended injuries. An experiment was conducted to test the hypothesis that inclusion of such ment...
Abstract Multiple regression models that include interactions between predictors are commonly reported in the communication literature. Ho wever, there are published instances where investigators misinterpreted the coefficients corresponding to variables that are used to form interaction terms. We briefly outline the interpretation of such coeffici...
This study investigates turnover intentions in public accounting firms using organizational justice. In the proposed theoretical model, the key construct is promotion instrumentality, the belief that the organization rewards strong employee performance with promotions. Employee perceptions of distributive justice influence promotion instrumentality...
Prior research has found strong evidence of a prospective association between R movie exposure and teen smoking. Using parallel process latent-growth modeling, the present study examines prospective associations between viewing of music video channels on television (e.g., MTV and VH-1) and changes over time in smoking and association with smoking p...
Most treatments of indirect effects and mediation in the statistical methods literature and the corresponding methods used by behavioral scientists have assumed linear relationships between variables in the causal system. Here we describe and extend a method first introduced by Stolzenberg (1980)55.
Stolzenberg , R. M. 1980. The measurement and de...
Hayes, Glynn, and Shanahan (2005a17.
Hayes , A. F. , Glynn , C. J. and Shanahan , J. 2005a . Willingness to self-censor: A construct and measurement tool for public opinion research . International Journal of Public Opinion Research , 17 : 298 – 323 . [CrossRef], [Web of Science ®]View all references) introduced the Willingness to Self-Censor Scale...
The casualties hypothesis predicts that as the casualties suffered by a nation mount during a military intervention, public opinion will turn against the intervention and its people will demand troop withdrawal. We use the U.S. war in Iraq as a context for testing the perceived casualties hypothesis, which predicts that public beliefs about the act...
Understanding communication processes is the goal of most communication researchers. Rarely are we satisfied merely ascertaining whether messages have an effect on some outcome of focus in a specific context. Instead, we seek to understand how such effects come to be. What kinds of causal sequences does exposure to a message initiate? What are the...
In academic and policy circles, it is believed that the American public is casualties-averse when sending its troops into war and that as casualties mount the public will increasingly call for withdrawal of troops from foreign military interventions. This study tests a variant of this “casualties hypothesis” by examining whether the public conceptu...
Prior research on knowledge gap effects, in health as well as in other domains, has focused largely on assessing individual-level differences in exposure to news based on self-report of media use. Inherent inferential limitations of this approach are addressed by testing the hypothesis that the relationship between education and cancer prevention k...
Researchers often hypothesize moderated effects, in which the effect of an independent variable on an outcome variable depends on the value of a moderator variable. Such an effect reveals itself statistically as an interaction between the independent and moderator variables in a model of the outcome variable. When an interaction is found, it is imp...
Evidence for media effects in survey research often depends upon measures of self-reported attention to various types of media content, under the assumption that such attention measures gauge the extent of cognitive processing of content. However, effects associated with self-reports of attention might often be due to reverse causation (the attitud...
Hypotheses involving mediation are common in the behavioral sciences. Mediation exists when a predictor affects a dependent variable indirectly through at least one intervening variable, or mediator. Methods to assess mediation involving multiple simultaneous mediators have received little attention in the methodological literature despite a clear...
When the errors in an ordinary least squares (OLS) regression model are heteroscedastic, hypothesis tests involving the regression coefficients can have Type I error rates that are far from the nominal significance level. Asymptotically, this problem can be rectified with the use of a heteroscedasticity-consistent covariance matrix (HCCM) estimator...
Communication scientists routinely ask questions about causal relationships. Whether it is examining the persuasive impact of public service announcements on attitudes and behavior, determining the impact of viewing political debates on political knowledge or voter turnout, or assessing whether success in achieving one's Internet browsing goals pro...
Many books on statistical methods advocate a 'conditional decision rule' when comparing two independent group means. This rule states that the decision as to whether to use a 'pooled variance' test that assumes equality of variance or a 'separate variance' Welch t test that does not should be based on the outcome of a variance equality test. In thi...
In almost all studies investigating spiral of silence theory, the outcome variable has been a person's reported willingness to express his or her opinion or engage others in a conversation. Research to date is largely silent on strategies that people might use to avoid speaking their opinion when it is requested by an audience hostile to that opini...
Homoskedasticity is an important assumption in ordinary least squares (OLS) regression. Although the estimator of the regression parameters in OLS regression is unbiased when the homoskedasticity assumption is violated, the estimator of the covariance matrix of the parameter estimates can be biased and inconsistent under heteroskedasticity, which c...
Using experimental data from a split-ballot survey conducted just after the 2004 U.S. presidential election, we tested competing predictions from reactance and balance theories on the effect of government censorship of images of ceremonies that include caskets containing dead U.S. soldiers on interest in viewing such images. In contrast to the reac...
This study (a nationally representative telephone survey; n = 406) examines how attention to accident and crime stories among adolescents predicts judgments regarding alcohol-related risks, and how effects of 2 relevant individual difference variables—sensation seeking and negative 1st- or 2nd-hand personal experiences with alcohol risks—are mediat...
This article provides researchers with a guide to properly construe and conduct analyses of conditional indirect effects, commonly known as moderated mediation effects. We disentangle conflicting definitions of moderated mediation and describe approaches for estimating and testing a variety of hypotheses involving conditional indirect effects. We i...
In content analysis and similar methods, data are typically generated by trained human observers who record or transcribe textual, pictorial, or audible matter in terms suitable for analysis. Conclusions from such data can be trusted only after demonstrating their reliability. Unfortunately, the content analysis literature is full of proposals for...
To examine the emergent properties of information seeking in hyperlinked environments, in this paper we developed a cyclic model. Using this model as a framework, the relationships among perceived goal difficulty, goal success, and self-efficacy were examined. Self-efficacy was conceptualized as a mediating mechanism and intrinsic motivation (IM) i...
Multilevel modeling (MLM) is growing in use throughout the social sciences. Although daunting from a mathematical perspective, MLM is relatively easy to employ once some basic concepts are understood. In this article, I present a primer on MLM, describing some of these principles and applying them to the analysis of a multilevel data set on doctor–...
In this introduction to the special issue on applications of multilevel modeling (MLM) to communication research, we provide a conceptual overview of the benefits of MLM—the ability to simultaneously analyze data collected at multiple levels, the ease with which it can be used to assess trends and change over time, and its incorporation of the nest...
In a polarized opinion climate, people may refrain from participating in publicly observable political activities that make them vulnerable to scrutiny and criticism by others who hold opinions that differ from their own. We took a dispositional approach to testing this claim by determining whether people who are relatively more influenced by the c...
This study examined how change in posttraumatic stress disorder (PTSD) symptoms relates to change in quality of life. The sample consisted of 325 male Vietnam veterans with chronic PTSD who participated in a randomized trial of group psychotherapy. Latent growth modeling was used to test for synchronous effects of PTSD symptom change on psychosocia...
This study examines associations between measures of stock exchange disclosure and market development at 50 of the member stock exchanges of the World Federation of Exchanges. We focus on stock exchange disclosure systems (rather than actual company disclosures) because this approach links stock exchange policy with desired outcomes related to mark...
The purpose of this study was to examine more closely the assumptions of causality in research on communication and political knowledge. Although most communica-tion theory suggests that communication causes learning, some have argued for the reverse causal direction or reciprocal causality. Others have confounded these con-cepts—in conjunction wit...
We define self-censorship as the withholding of one’s true opinion from an audience perceived to disagree with that opinion. Willingness to self-censor can be conceptualized as an individual difference, and we introduce here an 8-item self-report
instrument to measure this construct. The instrument yields reliable data in both student and nonstuden...
Hayes, Glynn, and Shanahan (2005) defined self-censorship as the withholding of one's opinion around an audience perceived to disagree with that opinion. They argued that people differ in their willingness to self-censor and introduced an 8-item self-report instrument, the Willingness to Self-Censor scale, to measure this individual difference. The...
Researchers often conduct mediation analysis in order to indirectly assess the effect of a proposed cause on some outcome through a proposed mediator. The utility of mediation analysis stems from its ability to go beyond the merely descriptive to a more functional understanding of the relationships among variables. A necessary component of mediatio...
This paper addresses a gap in the international literature aimed at understanding the impact of the marketing mix on choosing and upgrading business-to-business financial services dealers. This study involves two important financial services markets (foreign exchange and bonds) in two leading countries in financial services (the United States and t...
This study investigated whether perceptions of criminal psychological profiles are influenced by the identity of the profile's author. Police officers were given a profile they were told was written by either a professional profiler or by an unspecified author. When judged in relation to the actual perpetrator of the crime, police officers tended t...
This study examines associations between measures of stock exchange disclosure and market liquidity at the 50 member stock exchanges of the World Federation of Exchanges. We focus on stock exchange disclosure systems (rather than actual company disclosures) because this approach links stock exchange and government policy with desired outcomes relat...
Although psychological profiling has achieved wide acceptance in law enforcement investigations, there has been little empirical research into the skills required for profiling. One attribute that is frequently cited as quintessential for effective profiling is experience in police investigations. In a study similar in design to Kocsis, Irwin, Haye...
We examined how people's willingness to speak their opinions in a real situation varied as a function of perceived support for those opinions. When given a list of six potential topics to discuss with a real group of people, the participants reported a greater willingness to discuss a topic if they perceived greater support for their own opinions o...
The Stouffer z method, and other popular methods for combining p values from independent significance tests, suffer from three problems: vulnerability to criticisms of the individual studies being pooled, difficulty in handling the "file drawer problem," and vague conclusions. These problems can be reduced or eliminated by supplementing a test of c...
There has been little empirical study of the abilities contributing to proficient performance in psychological profiling. The authors sought to address this issue by comparing the accuracy of psychological profiles for a closed murder case generated by groups differing primarily in characteristics posited to underlie the profiling process. In addit...
Randomization tests are valid alternatives to parametric tests like the t test and analysis of variance when the normality
or random sampling assumptions of these tests are violated. Three SPSS programs are listed and described that will conduct
approximate randomization tests for testing the null hypotheses that two or more means or distributions...
Chow illustrates the important role played by significance
testing in the evaluation of research findings. Statistics and the
goals of research should be treated as both interrelated and separate
parts of the research evaluation process – a message that will
benefit all who read Chow's book. The arguments are especially
pertinent to the debate...
The practice of criminal psychological profiling makes frequent appeal to ataxonomic distinction between organised and disorganised offenders. Previous empirical studies claimed to validate this typology nevertheless have been methodologically inadequate. Using arson as a context this study analysed the crime scene characteristics of profit‐motivat...
The Stouffer method of adding Zs is the most familiar and widely used method for pooling the significance levels of multiple hypothesis tests. However, this method requires the assumption under the null hypothesis that the outcomes of the tests are statistically independent. A method for pooling the significance of nonoverlapping, or "doubly nonind...
We report a meta-analysis of survey studies examining the relationship
between people's perceptions of support for their opinions and their
willingness to express those opinions, Evidence from the analysis
indicates the presence of a very small, but statistically significant,
relationship between the degree to which a person believes others hold
si...
Bailer (1989) recommended a randomization test equivalent of the F ratio test of variance equality when sampling from nonnormal populations. Simulation data are presented here to illustrate that this method of testing variance equality is not valid when the population means differ and thus should not be routinely used. Two alternative methods of te...
The relationship between trait ambiguity and self-peer agreement in personality judgment was examined. In Study 1, self-peer agreement was lower on ambiguous traits (those with many behavioral referents) than on unambiguous ones (those with few behavioral referents). This finding was partially moderated by the level of friendship between peers. The...
People often disagree in their judgments of the traits and the abilities of others. Three studies suggested that these differences arise because people activate and use their own particular behaviors as norms when evaluating the performances of others. In Study 1, 71% of participants reported comparing a target's behavior with their own behavior wh...
Citations
... It seems plausible to assume that people's expression of political opinions also varies in accordance with the level of message persistence (Lane et al., 2019). Previous spiral of silence research suggested that situational factors, that is, characteristics of the communication setting (e.g., the size of the audience; Salmon & Oshagan, 1990) can influence people's willingness to voice their political views (Matthes & Hayes, 2014;Perry & Gonzenbach, 2000;Shamir, 1997). Noelle-Neumann (1994) herself pointed out the potential impact of situational factors and argued that silencing mechanisms may not be detectable in circumstances that are too private (e.g., talking to close friends) or too public (e.g., giving a TV interview). ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/352957360033796-1461163001045_Q64/Joerg-Matthes.jpg)
... (Cohen, 1988). Next, both direct and indirect effect analyses were conducted using PROCESS (Hayes et al., 2008). This is a conditional process model that utilizes an ordinary least squares-based path analytical framework (Hayes, 2017). ...
... In this study, the two mediator variables (positive and negative religious coping) were included in the mediator model at the same time. This multiple mediation model method has been recommended in recent research (Coutts & Hayes, 2022). Coutts and Hayes (2022) argue that a mediation model is more likely to be realistic if it is designed to capture multiple mechanisms at the same time with the inclusion of more than one mediator. ...
... Using PROCESS macro (version 3.3) model 4 of SPSS, 33 we tested the mediation model; psychological distress was taken as a predictor, IL-1β, TNF-α, and IL-4 as mediators, and cognitive function (MMSE) as the outcome variable. PROCESS Model 4 examined the effect of psychological distress on IL-1β, TNF-α, and IL-4 (A path), IL-1β, TNFα, and IL-4 on cognitive function (B path), the aggregate effect of the psychological distress on cognitive function (C path), and the direct effect of the psychological distress on the cognitive function in this model (C′ path). ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281112832747-1673557577340_Q64/Juan-Jose-Igartua.jpg)
... Cronbach's alpha is an estimate of total-score reliability under the assumption that the factor loadings are equal across all items (i.e. essential tau equivalence) (Hayes & Coutts, 2020). ...
... First, we performed ordinal logistic regressions to establish the mediation based on Baron & Kenny's 4-step method (Baron & Kenny, 1986). Secondly, we conducted a simple mediation analysis using IBM SPSS ® Hayes' PROCESS macro to verify our Baron & Kenny 4-step mediation analysis (Coutts et al., 2019;Hayes, 2018). ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281087397369-1664572151148_Q64/Tao-Jiang-133.jpg)
... The validity is the essential characteristic of the constructs to be considered in the research study evaluated through the convergent and discriminant validity of the constructs (Hair et al., 2022;Lu et al., 2020), The convergent validity of the constructs was ensured through the criteria such as AVE, composite reliability, and Cronbach's alpha to evaluate the internal consistency of the items and the higher values of AVE, Cronbach's alpha, and the composite reliability evaluates the convergent validity of the scale's further analysis for the study (Hair et al., 2022), The values of the discriminant validity were to be considered through the Fornell, Larcker (1981) defined criteria explained that the square root of AVE has to be greater than the correlations between the constructs (Ahmed et al., 2020), The structural model hypotheses associated with the research questions related to the relationship with the conceptualized paths. The survey data were examined through partial least square structural equation modelling and the analysis of the mediation through a bootstrapping technique to test the indirect effects (Hayes, Rockwood, 2020), Table 1 includes the details of the respondent demographic information. In this research study, more than 1000 responses were collected through physical questionnaires and with the help of the internet through a google survey form. ...
... To test for the moderation effects of managerial social capital and managerial cognition on the indirect effect of the two managerial human capital dimensions on firm performance through DBMT, a moderated mediation analysis was conducted using meancentered product terms (Model 7 by Hayes, 2018b). Additionally, significant interaction terms in the regression model were probed by computing conditional effects using simple slopes at the mean and one standard deviation above and below it (Hayes, 2018a;Preacher et al., 2006). ...
... Adopting the PROCESS macro over structural equation modelling (SEM) has several benefits. First, the macro is more useful than SEM when nearly identical estimates of path coefficients and conditional indirect effects are obtained (with only a few discrepancies at the third decimal place; Hayes et al., 2017). Second, SEM, which frequently involves simultaneous estimation using the maximum likelihood method, is generally most optimal for large-sample analyses; the standard errors generated by this method tend to be biased downward in small samples (Hayes et al., 2017;Hoogland & Boomsma, 1998). ...
... To test the effect of WMC on tactical decision-making and its dependence on the level of soccer expertise, we utilized a moderation analysis with a multi-categorical moderator. Given the hypothesis on the superior tactical decision-making of professional soccer players, we used Helmert coding for levels of expertise (Hayes & Montoya, 2017). The regression coefficients (bs) of this method estimate the difference between the mean of professional soccer players and the unweighted mean of amateur and recreational soccer players (D 1 ) and the difference between the mean of amateur and recreational soccer players (D 2 ). ...
