Measures of Effect Size for Comparative Studies: Applications, Interpretations, and Limitations.

By Stephen Olejnik, James Algina. Contemporary Educational Psychology, 2000

732 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/1d29b1cd2e59885985aff94c663b82d5517cfe01

How researchers see this paper

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

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Direct Instruction of Metacognition Benefits Adolescent Science Learning, Transfer, and Motivation: An In Vivo Study. (2015, methodology): “We interpret effects as small when p2 0.06 or d 0.2, medium when 0.06 p2 0.14 or 0.3 d 0.8, and large when p2 0.14 or d 0.8 (see Cohen, 1988; Olejnik & Algina, 2000).”
A systematic review of effect size in software engineering experiments (2007, background): “Formulas based on t-values and other statistics, as well as estimators that adjust for bias, are provided in [24,28,31,32,35].”
Reporting Effect Size Estimates in School Psychology Research. (2006, methodology): “The formula for the Sum of Squares Contrast (SScontrast ), adapted from Olejnik and Algina (2000), is:”
What Future Quantitative Social Science Research Could Look Like: Confidence Intervals for Effect Sizes (2002, background): “Short and accessible treatments of effect size choices have been provided by Kirk (in press), Olejnik and Algina (2000), Snyder and Lawson (1993), and Thompson (2002).”
Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs (2013, methodology): “In between-subjects designs with ﬁxed factors ω 2 and ω 2 p can be calculated through the formulas provided by Olejnik and Algina (2000) and Bakeman (2005): For within-subjects designs, ω 2 p is calculated in the same way as for between-subjects designs (see above), but ω 2 is calculated by:…”
Reading Motivation: Exploring the Elementary Gender Gap (2010, methodology): “Effect size was computed using the difference of the adjusted means (between girls and boys) on MRP scores divided by the pooled standard deviation (AERA, 2006; Olejnik & Algina, 2000; Thompson, 1996).”
Effects of a Cooperative Learning Program on the Elaborations of Students During Help Seeking and Help Giving (2005, methodology): “The effect sizes in the present study were therefore computed by dividing the difference between the adjusted cell means in the contrast by the pooled standard deviation for all of the cells in the between-subjects design (Olejnik & Algina, 2000).”
A unified approach to measuring the effect size between two groups using SAS (2012, unknown): “The third one is that population heterogeneity increases error variance and reduces the magnitude of the effect size [14, 15].”
Effectiveness of holistic mental model confrontation in driving conceptual change (2012, unknown): “We followed the guidelines by Cohen (1988; see also Olejnik & Algina, 2000) according to which effects are regarded as small when h p 2 < .06, medium when h p 2 < .14, and large when h p 2 > .14.”
Estimating Effect Sizes From Pretest-Posttest-Control Group Designs (2008, methodology): “Although methods exist to deal with more complex designs (Cortina & Nouri, 2000; Olejnik & Algina, 2000; Rosenthal, 1994), the focus of past research has been on obtaining effect size estimates that are comparable to those from a simple twogroup study.”
Effect-Size Measures and Meta-Analytic Thinking in Counseling Psychology Research (2006, background): “ Olejnik and Algina (2000) provided a particularly thorough discussion of variability’s role in group-comparison designs.”
Cautionary Note on Reporting Eta-Squared Values from Multifactor ANOVA Designs (2004, background): “To the contrary, there are situations in which a partialled measure is pre- at GEORGE WASHINGTON UNIVERSITY on August 13, 2016epm.sagepub.comDownloaded from ferred over a classical measure (Breaugh, 2003; Cohen, 1973; Haase, 1983; Keren & Lewis, 1979; Olejnik & Algina, 2000).”
The Efficacy of two Improvement-Over-Chance Effect Sizes for Two-Group Univariate Comparisons under Variance Heterogeneity and Nonnormality (2001, background): “(pp. 25-26) Two popular approaches for estimating the magnitude of an effect are the standardized mean difference, δ (Cohen, 1988; Glass, 1977; Hedges, 1981), and measures of association such as η2 and ω2(Olejnik & Algina, 2000; Richardson, 1996).”