In addition to examining the overall results of combined studies in a meta-analysis, it is also important to look for potential moderators, even in the absence of heterogeneity. Categorical models for examining potential moderators in meta-analysis consist of ANOVA like models for assessing within and between-group differences. Weighted least-squares regression models are used to examine associations and potential predictors of the primary outcome. For more information on moderator analysis see Hedges LV, Olkin I. Statistical methods for meta-analysis. San Diego, California Academic Press, 1985.