The purpose of this paper is to demonstrate how many more subjects are required to achieve equal power when testing certain hypotheses concerning proportions if the randomized response technique is employed for estimating a population proportion instead of the conventional technique. (Author)

McNemar's discussion of error reduction in a mixed two-group design fails to provide an algebraic presentation of this error reduction. This paper presents not only the algebraic development of the error term but shows that under certain conditions mixing may increase experimental error. (Author)

A review and meta-analysis were made of placebo control groups in educational experiments. In all, 125 studies were clustered into procedures that included (1) explicit manipulation of attentional elements; (2) explicit description of the placebo activity plus implied reference to attention; and (3) exclusive reference to the activity. (SLD)