Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs
By Daniël Lakens. Frontiers in Psychology, 2013
9,290 citations recorded by the source corpus.
Effect sizes are the most important outcome of empirical studies. Most articles on effect sizes highlight their importance to communicate the practical significance of results. For scientists themselves, effect sizes are most useful because they facilitate cumulative science. Effect sizes can be used to determine the sample size for follow-up studies, or examining effects across studies. This article aims to provide a practical primer on how to calculate and report effect sizes for t-tests and ANOVA's such that effect sizes can be used in a-priori power analyses and meta-analyses. Whereas many articles about effect sizes focus on between-subjects designs and address within-subjects designs only briefly, I provide a detailed overview of the similarities and differences between within- and between-subjects designs. I suggest that some research questions in experimental psychology examine inherently intra-individual effects, which makes effect sizes that incorporate the correlation between measures the best summary of the results. Finally, a supplementary spreadsheet is provided to make it as easy as possible for researchers to incorporate effect size calculations into their workflow.
Subfields: Applied Psychology, Experimental and Cognitive Psychology, Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/c65c650de3de909adfa0028d170e21489000162c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Applied Psychology
- S. van der Linden
- C. Brydges
- Christiany Suwartono
- T. Bouman
- W. Poortinga
- E. Peters-Burton
- Stephanie M. Stehle
- Maciej Tomczak
In Experimental and Cognitive Psychology
- Christiany Suwartono
- C. Brydges
- Casper J. Albers
- E. Peters-Burton
- Stephanie M. Stehle
- Maciej Tomczak
- Ewa Tomczak
- Joseph P. Vitta
In Statistics and Probability
- Ali H. Al-Hoorie
- Joseph P. Vitta
- C. Brydges
- Christiany Suwartono
- Casper J. Albers
- Jin X. Goh
- Judith A. Hall
- Luke Plonsky
Citations in the corpus
- Eta- and partial eta-squared in L2 research: A cautionary review and guide to more appropriate usage (2018, background): “And perhaps it further ‘indicates that researchers are either very passionate about unnecessary subscript letters [i.e. p for partial], or rely too much on the effect sizes as they are provided by statistical software packages’ (Lakens, 2013: 1).”
- Mindfulness-based stress reduction (MBSR) enhances distress tolerance and resilience through changes in mindfulness (2016, methodology): “For effect sizes, Hedges’s g was calculated (Cumming, 2012; Lakens, 2013), which is a more conservative unbiased version of Cohen’s d, correcting for differences in small and dissimilar samples sizes.”
- Estimating the Reproducibility of Experimental Philosophy (2018, methodology): “We are also indebted to Lakens’ R2D2 sheet (Lakens, 2013).”
- Equivalence Tests (2017, neutral): “Although using these benchmarks to interpret effect sizes is typically recommended as a last resort (e.g., Lakens, 2013), their use in setting equivalence bounds seems warranted by the lack of other clear-cut recommendations.”
- Gratitude and health: An updated review (2019, methodology): “If effect sizes were not reported in the original paper, they were estimated based on available data, using the method reported by Lakens (2013).”
- Mini Meta-Analysis of Your Own Studies: Some Arguments on Why and a Primer on How (2016, methodology): “Cohen (1992), Rosnow and Rosenthal (2009), and Lakens (2013) provide primers on ES, including procedures for deriving them from the results provided in the original studies.”
- When power analyses based on pilot data are biased: Inaccurate effect size estimators and follow-up bias (2018, methodology): “An unbiased estimate of Cohen's d is called Hedges' g (see Lakens, 2013), and recommendations in this article concerning the use of ω 2 and ε 2 instead of η 2 extend to the use of Hedges' g instead of Cohen's d .”
- The development and psychometric properties evaluation of the Indonesian version of the Wechsler Adult Intelligence Scale - Fourth Edition (WAIS-IV) (2018, methodology): “The Cohen’s d score was also calculated (Lakens, 2013).”
- A primer on investigating the after effects of acute bouts of physical activity on cognition (2019, methodology): “The use of the pooled standard deviation ultimately makes this formula only appropriate to utilize for between-subjects designs (Lakens, 2013).”
- Effect Size Guidelines, Sample Size Calculations, and Statistical Power in Gerontology (2019, methodology): “Cohen’s d values were converted to Hedges’ g (Lakens, 2013; Formula 4), as these values are directly comparable to each other, and Hedges’ g accounts for biased estimates of effect size, especially in small sample sizes (Cumming, 2012).”