How to select, calculate, and interpret effect sizes.

By J. Durlak. Journal of Pediatric Psychology, 2009

1,454 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/f10a31e2018795e0b7f4dbc0bdc910cbab5c9601

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Management Science and Operations Research

Citations in the corpus

Predictors of foster care exits to permanency: A competing risks analysis of reunification, guardianship, and adoption (2011, background): “First, large samples can sometimes lead to many statistically significant findings even when the relationships could be considered trivial (Durlak, 2009; Vaske, Gliner, & Morgan, 2002).”
Synthesizing Results From Empirical Research on Computer-Based Scaffolding in STEM Education (2016, background): “When interpreting effect sizes, one should refer to (a) effect sizes of similar interventions targeting similar outcomes, (b) the gain in the target outcomes that one would see among target learners without an intervention, and (c) practical significance (Durlak, 2009; Hill, Bloom, Black, & Lipsey, ”
Keep Using My Health Apps: Discover Users' Perception of Health and Fitness Apps with the UTAUT2 Model (2015, neutral): “022.(32) The standard deviations of social influence and facilitating conditions were not too small (1.”
Beyond small, medium, or large: points of consideration when interpreting effect sizes (2019, methodology): “It provides an assessment of the strength of findings that tests of statistical significance alone do not provide (Balow, 2017; Coe, 2002; Durlak, 2009; Sullivan & Feinn, 2012).”
Sourcing in Text Comprehension: a Review of Interventions Targeting Sourcing Skills (2018, neutral): “In those cases, we calculated an “adjusted” ES by subtracting the pre-ES from the post-ES, following the guidelines suggested by Durlak (2009).”
The need to report effect size estimates revisited. An overview of some recommended measures of effect size (2014, background): “Relying on the p-value alone for statistical inference does not permit an evaluation of the magnitude and importance of the obtained result [10, 12, 13].”
Short-Term Exposure to Nature and Benefits for Students’ Cognitive Performance: a Review (2021, methodology): “For studies that reported the same preand post-test scores, we computed ES by subtracting the pre-ES from the post-ES, 1 3 1 3 as suggested by Durlak (2009).”
Evaluation of and support for group prototypical leaders: a meta-analysis of twenty years of empirical research (2017, methodology): “This measure of effect size is chosen for two reasons; it is the more common in the literature concerning prototypicality and leader ratings, and these latter constructs are generally measured on a Likert scale, and are therefore continuous data (Durlak, 2009; Hedges, 2008).”
Scaffolding Narrative Skills: A Meta-Analysis of Instruction in Early Childhood Settings (2017, background): “The standardized mean difference reported is Hedges’s g, which corrects for upward bias in the case of small samples (Durlak, 2009).”
Meta-analysis of data from animal studies: a practical guide. (2014, neutral): “A number of methods re available, each with their merits (for example see: Nakagawa nd Cuthill, 2007; Baguley, 2009; Durlak, 2009).”
Impact of plant invasions on local arthropod communities: a meta‐analysis (2014, background): “…on statistical effect sizes rather than absolute differences and explicit testing for potential confounding effects and by restricting the objective of our search (Walker, Hernandez & Kattan 2008; Durlak 2009) to studies that quantified arthropods in both the invaded and noninvaded habitat.”
A Meta‐Analysis on the Effects of Text Structure Instruction on Reading Comprehension in the Upper Elementary Grades (2020, background): “Although effect sizes of approximately 0.20 are generally classified as small, we interpret them as meaningful because they were obtained in educational contexts, where even effect sizes that are generally classified as small are of interest (see Durlak, 2009; Hedges & Hedberg, 2007).”