Effect-Size Indices for Dichotomized Outcomes in Meta-Analysis.

Abstract

It is very common to find meta-analyses in which some of the studies compare 2 groups on continuous dependent variables and others compare groups on dichotomized variables. Integrating all of them in a meta-analysis requires an effect-size index in the same metric that can be applied to both types of outcomes. In this article, the performance in terms of bias and sampling variance of 7 different effect-size indices for estimating the population standardized mean difference from a 2 × 2 table is examined by Monte Carlo simulation, assuming normal and nonnormal distributions. The results show good performance for 2 indices, one based on the probit transformation and the other based on the logistic distribution.In the last 20 years, meta-analysis has become a very popular and useful research methodology to integrate the results of a set of empirical studies about a given topic. To carry out a meta-analysis an effectsize index has to be selected to translate the results of every study into a common metric.When the focus of a study is to compare the performance of two groups (e.g., treated vs. control, male vs. female, trained vs. nontrained) on a continuous dependent variable, the effect-size index most usually applied is the standardized mean difference, d, defined as the difference between the means of the two groups divided by a within-group standard deviation estimate. Substantial meta-analytic literature has been devoted to showing the properties of this index, its sampling variance, how to obtain confidence intervals on the weighted mean effect size obtained from it, its statistical significance, homogeneity tests, and how to search for variables that moderate it (

Probabilistic Interval Forecasts: An Individual Differences Approach to Understanding Forecast Communication

“…For each additional unit increase in WMC score, the likelihood of successful interpretation increased by 1.01, Exp( ) = 1.01, < .001, 2 (1, = 320) = 7.03, < .001. However, both effect sizes [36] were small ( < .10), suggesting that numeracy and working memory limitations provide only a partial explanation for these errors.…”

Efficacy of HIV/STI Behavioral Interventions for Heterosexual African American Men in the United States: A Meta-Analysis

“…For studies reporting means and standard deviations for continuous variable outcomes, standardized mean differences were calculated and then converted into odds ratio values [31]. An odds ratio of\1 indicates a reduction in odds of HIV sexual risk behavior or STI outcomes in the intervention group relative to the comparison group.…”

Single-Session Alcohol Interventions for Heavy Drinking College Students: A Systematic Review and Meta-Analysis

“…All effect sizes were adjusted with the small-sample correction factor (Hedges, 1981). When success/failure rates rather than means/standard deviations for each group were provided, odds ratio effect sizes were transformed to the standardized mean difference using the Cox transformation (described in Sánchez-Meca et al, 2003).…”

“…Standard errors were calculated for all effect sizes using accepted formulas (Lipsey & Wilson, 2001;Sánchez-Meca et al, 2003). When effect size estimates originated from cluster-randomized trials in which the authors did not properly account for the cluster design in their own analyses, standard errors were inflated by the design effect (Higgins et al, 2008).…”