An appropriate estimate of statistical power is critical for the design of intervention studies. Although the inclusion of a pretest covariate in the test of the primary outcome can increase statistical power, samples selected on the basis of pretest performance may demonstrate range restriction on the selection measure and other correlated…

There are several goals guiding this study. First, the authors use an experimental design to examine the causal effects of giving children 10 self-selected books over two summers. Second, they examine whether treatment effects are moderated by children's family income (i.e., eligibility for free- and reduced-price lunch). As a result, they examine…