Reporting point and interval estimates of effect-size for planned contrasts: fixed within effect analyses of variance

The purpose of this tutorial is threefold: (a) review the state of statistical science regarding effect-sizes, (b) illustrate the importance of effect-sizes for interpreting findings in all forms of research and particularly for results of clinical-outcome research, and (c) demonstrate just how easily a criterion on reporting effect-sizes in research manuscripts can be accomplished. The presentation centers on within-effect analyses of variance including the one-way design for testing pre-post hypotheses and the two-way parallel-groups design for making direct comparisons of competing treatment protocols (e.g., experimental treatment versus control). The presentation is supported with worked examples and a web site containing templates for software applications.

The reader will be able to: (1) explain the rationale for the increased use of estimates of effect-size in reporting results in published research manuscripts; (2) describe what an effect-size is (generally considered) and provide a rationale for its importance; (3) distinguish among the many forms of effect-size and apply their features to the most appropriate choices under specific research circumstances; and (4) appropriately report and interpret effect-sizes.