ArticlePDF Available

A Power Primer

Authors:

Abstract

One possible reason for the continued neglect of statistical power analysis in research in the behavioral sciences is the inaccessibility of or difficulty with the standard material. A convenient, although not comprehensive, presentation of required sample sizes is provided. Effect-size indexes and conventional values for these are given for operationally defined small, medium, and large effects. The sample sizes necessary for .80 power to detect effects at these levels are tabled for 8 standard statistical tests: (1) the difference between independent means, (2) the significance of a product-moment correlation, (3) the difference between independent rs, (4) the sign test, (5) the difference between independent proportions, (6) chi-square tests for goodness of fit and contingency tables, (7) 1-way analysis of variance (ANOVA), and (8) the significance of a multiple or multiple partial correlation.
TutorialsinQuantitativeMethodsforPsychology
2007,Vol.3(2),p.79.
Apowerprimer
JacobCohen
NewYorkUniversity
Onepossiblereasonforthecontinuedneglectofstatisticalpower
analysisinresearchinthebehavioralsciencesistheinaccessibilityofor
difficultywiththestandardmaterial.Aconvenient,althoughnot
comprehensive,presentationofrequiredsamplesizesisprovided.
Effectsizeindexesandconventionalvaluesforthesearegivenfor
operationallydefinedsmall,medium,andlargeeffects.Thesample
sizesnecessaryfor.80powertodetecteffectsattheselevelsaretabled
for8standardstatisticaltests:(1)thedifferencebetweenindependent
means,(2)thesignificanceofaproductmomentcorrelation,(3)the
differencebetweenindependentrs,(4)thesigntest,(5)thedifference
betweenindependentproportions,(6)chisquaretestsforgoodnessof
fitandcontingencytables,(7)1wayanalysisofvariance(ANOVA),
and(8)thesignificanceofamultipleormultiplepartialcorrelation.
FromPsychologicalBulletin(1992),vol112(1),p.155159.Copyright©1992bytheAmericanPsychological
Association. Reproducedwithpermission. Forinformationonhowtoobtainthefulltexttothisarticle,
pleasevisithttp://www.apa.org/psycarticles.
79
Article
This study aimed to evaluate the effectiveness of a childbirth education program on self-efficacy and state anxiety among first-time Jordanian mothers. A randomized controlled trial was conducted using pretest/posttest design with 128 low-risk, first-time Jordanian mothers. The experimental group (N = 64) received a childbirth education program, while those in the control group (N = 64) received standard care in antenatal clinics. Data were collected at two different time points: at recruitment and 3 weeks after attending the program. The mean score of the experimental group on outcome expectancy (posttest) (139.91, SD = 15.586) was significantly higher than that of the control group (110.16, SD = 28.33) (F = 72.356, P = .003, partial Eta squared = .37). On the efficacy expectancy, the mean score of the experimental group (133.33, SD = 16.246) was also higher than that of the control group (92.06, SD = 27.07) (F = 144.282, P = .000, partial eta squared = .54). On the state anxiety scale, the mean score of the experimental group was significantly lower than that of the experimental group (F = 89.715, P = .002, partial eta squared = .42). The childbirth education program improved the coping ability of mothers during childbirth and decreased their state of anxiety.
Article
Full-text available
Given the prevalence of transfer activity, education stakeholders must understand how transfer may be associated with student outcomes. Such knowledge is critical, as the COVID-19 pandemic and economic downturn have impacted college enrollment and student transfer behavior. Relying on a sample of 6510 undergraduate students from BPS:12/17 data, we conducted analyses using multiple regression to examine the relationship between student transfer direction and two student outcomes: time to degree and cumulative loan debt. Further, we analyzed whether these relationships varied by income status, using adjusted gross income (AGI) as a proxy. We found that transferring from one postsecondary institution to another may extend time to degree by one academic semester and result in increased student loan debt, with these findings varying by income level.
Article
Full-text available
Introduction During the early beginnings of COVID-19, service providers were forced to close their doors and move their services online, causing significant disruptions for many families and communities, such as those with intellectual and developmental disabilities (IDD). In this study, we examined the extent to which COVID-19 disrupted services for the IDD community in California. Methods Secondary data were analyzed from a survey ( N = 1,082) disseminated by the Autism Society of California in May 2020. Respondents were placed into two categories: autism spectrum disorder (ASD) only ( n = 794) and IDD other than ASD ( n = 288). Results There were significant differences in services between diagnostic groups (<.05). There was a threefold difference in loss of respite services in the ASD (4.3%) versus the IDD group (12.9%). In the ASD group, 48.5% reported no change at all in respite services received, whereas in the IDD group, 71.5% reported no change. Before the pandemic, a higher mean number of medical and therapeutic services was reported as received in the ASD group ( M = 1.38) than in the IDD group ( M = 1.04). However, at the time of the survey, the IDD group reported a higher mean number of such services ( M = 1.32) than the ASD group ( M = 1.02). Differences were also seen by race/ethnicity. Before lockdown, there were no significant differences in the mean number of services reported by race/ethnicity among the full sample. However, at the time of the survey, a significantly higher mean number of services was reported by respondents who identified as White ( M = 1.26) compared to people of color ( M = .91), p < .05. Discussion To our knowledge, this study is the first to compare services received by IDD diagnostic groups during COVID-19. Findings help elucidate the negative impact of COVID-19 on the IDD community in California, as well as inform strategies for the ongoing and post-pandemic periods.
Article
Unlabelled: Rorschach and self-report instruments represent methodologically different types of assessment, which together may yield incremental information about the test-taker. There is little evidence on whether and when results from these methods converge. Objective: To examine possible convergences between Rorschach trauma-related personality variables and self-reported variables. Method: Before and after psychotherapy 22 traumatized adult refugee patients were assessed with the Rorschach Performance Assessment System (R-PAS), symptom checklists of posttraumatic stress, anxiety and depression, and a quality of life questionnaire. Correlational analyses between eight R-PAS variables and 10 self-reported variables were performed. Results: The findings showed inconsistent and nonsignificant correlations pretherapy. Posttherapy, however, all R-PAS variables except Complexity correlated positively with symptoms of mental disorder, and negatively with the quality of life variables, as predicted. The R-PAS variables Mutuality of Autonomy-Pathology, Poor Human Representation, Critical Content, and Form Quality-minus%, converged significantly with most of the self-reported variables, with medium to large correlations. Conclusion: The finding of convergence only after psychotherapy, may tentatively suggest greater self-knowledge and internal consistency through the therapy experience, and increased trust and self-disclosure through the repeated meetings with the researchers. The findings represent a promising contribution to a cumulative validation process of convergence between Rorschach and self-report data.
Article
Full-text available
Postsecondary institutional mission statements include goals of preparing students to become global citizens. Transformative learning theory is central to global citizenship education (GCE). Many postsecondary institutions provide GCE initiatives through the global competencies approach, which includes self-awareness in intercultural encounters, communications, and general knowledge about world issues. The purpose of this study was to explore perceptions of global citizenship and general knowledge of international food and agriculture issues. A cross-sectional design and random samples of university members provided data. Differences in perceptions of global civic engagement were found; faculty members were significantly more globally engaged. Graduate students had significantly more awareness of being global citizens. Respondents were unknowledgeable about international food and agriculture. Transformative learning and GCE may be incorporated into postsecondary education by using disorienting dilemmas to promote critical self-examination of worldviews. To enliven university missions of preparing global citizens, we must encourage meaningful actions from local to global levels.
Article
Objective - The present study investigates the impact of augmented reality (AR) on the learning abilities of primary and secondary students at the cognitive and affective levels. Methodology/Technique - The data of 59 relevant domestic and international studies between 2010 and 2021, including 83 studies and 4123 samples, were analyzed through CMA for meta-analysis. Finding - The overall effect size of AR technology on the teaching effectiveness of primary and secondary school students was 0.598, which had a positive contribution. The impact of AR technology on primary and secondary school students was stronger at the affective levels than at the cognitive levels. Novelty - In the process of learning with AR-assisted resources for primary and secondary school students, the school levels, teaching methods, and resource types did not differ significantly, and the differences in teaching outcomes were manifested in the different subject content. Type of Paper - Empirical Keywords: Augmented reality (AR); Learning effects; Meta-analysis; Primary and Secondary students; Cognitive; Affective. JEL Classification: I21, I26. Reference to this paper should be referred to as follows: Shen, Q; Tsai, P. (2022). The Impact of Augmented Reality on the Learning Abilities of Primary and Secondary Students at the Cognitive and Affective levels: A Meta-analysis, GATR-Global J. Bus. Soc. Sci. Review, 10(4), 220–228. https://doi.org/10.35609/gjbssr.2022.10.4(1)
Article
Objectives: The aim of this study was to analyze the effects of ten sessions of active transcranial direct current stimulation transcranial direct current stimulation (tDCS) (2 mA) with 13:20:13 stimulation at M1 in women with fibromyalgia (FM). To the best of our knowledge, this is the first article that uses this protocol in patients with FM. The main hypothesis is that the protocol would be effective in decreasing pain and that the results would last for up to 90 days. Materials and methods: This study was a randomized clinical trial with 35 women with FM divided into two groups, active tDCS group and sham tDCS group. A conventional tDCS device was used to deliver 2 mA for 13 minutes, with a 20-minute break followed by a further 13 minutes of stimulation for ten sessions. The anodal stimulus was in the left primary motor cortex M1 region. The primary outcome was a change in the visual analog scale and the Survey of Pain Attitudes pain score at the end of treatment, after 30 days, and 90 days after the end of treatment. Secondary outcomes included changes in the Fibromyalgia Impact Questionnaire, Hamilton Anxiety Rating Scale, Hamilton Depression Rating Scale, World Health Organization's Quality of Life Questionnaire, and Fatigue Assessment Scale. The Research Ethics Committee of the Centro Universitário da Grande Dourados under registration number Certificado de Apresentação de Apreciação Ética approved this research: 36444920.5.0000.5159. The study was registered in The Brazilian Registry of Clinical Trials with the identifier RBR-8wc8rjq. Results: The active tDCS group showed improvement in pain after ten sessions (p < 0.001), after 30 days (p < 0.01), and after 90 days (p < 0.001) compared with sham tDCS. In addition, improvement in quality of life (QoL) and fatigue was observed in the active tDCS group. Conclusion: The results of this study suggest that active tDCS with an intensity of 2 mA for ten sessions was effective in decreasing pain and fatigue and improving QoL in patients with FM.
Article
Several MS/PC—DOS programs are now available to help with statistical power analysis and sample-size choice. This article compares these programs with respect to the statistical methods they cover, their user interface, their ease of use, their graphics capabilities, and their computational accuracy.
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
The problem of testing statistical hypotheses is an old one. Its origins are usually connected with the name of Thomas Bayes, who gave the well-known theorem on the probabilities a posteriori of the possible “causes” of a given event.* Since then it has been discussed by many writers of whom we shall here mention two only, Bertrand† and Borel,‡ whose differing views serve well to illustrate the point from which we shall approach the subject.
Article
This is an account of what I have learned (so far) about the application of statistics to psychology and the other sociobiomedical sciences. It includes the principles "less is more" (fewer variables, more highly targeted issues, sharp rounding off), "simple is better" (graphic representation, unit weighting for linear com- posites), and "some things you learn aren't so." I have learned to avoid the many misconceptions that surround Fisherian null hypothesis testing. I have also learned the importance of power analysis and the determination of just how big (rather than how statistically significant) are the effects that we study. Finally, I have learned that there is no royal road to statistical induction, that the informed judgment of the investigator is the crucial element in the interpretation of data, and that things take time.
Some statistical issues in psychological research
  • J Cohen