Review of the Quantitative Quality

The goal of this study was to assess the statistical health of educational psychology literature, both current and past, to: (1) determine the range of effect sizes observed in the current literature (1998-1999); (2) determine the range of observed (or a posteriori) power in the current literature; (3) compare these two statistics to that of the discipline in past years (1939 and 1969); (4) assess the proportion of articles from each of those years reporting testing assumptions of statistical tests, effect size, or power; and (5) assess the reliability of measures used in this research. In all, 55 from 1969 and 96 from the current period were included in these analyses. Results were encouraging, suggesting that most educational psychology research encounters at least moderate (d=0.50) effect sizes, with average power (0.73) that is increasing over that observed in 1969. However, with only 36 % of educational psychology studies showing acceptable levels of power (0.80 according to Cohen), only 17% reporting effect sizes, only St reporting testing assumptions of statistical tests, and only 2 % reporting power, there is still a great deal of room for improvement in the field. (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the original document. Educational Psychology from a Statistician's Perspective: