When the results of a series of independent studies are combined, it is useful to quantitatively estimate the magnitude of the effects. Several methods for estimating effect size are compared in this paper. Glass' estimator and the uniformly minimum variance unbiased estimator are based on the ratio of the sample mean difference and the pooled within-group standard deviation. The third estimator is the maximum likelihood estimator. The fourth estimator is a shrunken form of the minimum variance unbiased estimator. All four estimators are shown to be equivalent in large samples, but they differ in finite samples. Two procedures for testing the fit of the data to the proposed structural model and for detection of outliers, an example of the application of the techniques, and a summary of recommendations on statistical procedures for estimation of effect size from a series of experiments are presented. (Author/BW)