Psychological Bulletin

Boneau, C. Alan

doi: 10.1037/h0041412pmid: 13802482

There has been an increase lately in the use of the frequently less powerful nonparametric statistical techniques particularly when the data do not meet the assumptions for t or analysis of variance. By means of empirical analysis and a mathematical frame of reference it is demonstrated that the probability values for both t, and by generalization for F are scarcely influenced when the data do not meet the required assumptions. One exception to this conclusion is the situation where there exists unequal variances and unequal sample sizes. In this case the probability values will be quite different from the nominal values. 22 refs.

Masling, Joseph

doi: 10.1037/h0044057pmid: 14422032

Despite the methodological flaws existing in studies concerned with the effects of method of test administration, testing situation, examiner influence, and subject influence on responses made to projective tests, there is strong evidence to show that these variables are important determiners of subject responses. One of the more important variables is the degree to which the S senses that the experimental conditions are integral to the total testing situations, i.e., if there is a feeling of high correspondence then S will be influenced. The implications for the client-clinician relationship are explored. 105 refs.

Humphreys, Lloyd G.

doi: 10.1037/h0043174pmid: 14405381

It has been stated elsewhere by Campbell and Fishe (see ^W34:^n 103) that trait validity values should be higher than the correlations among different traits measured by the same method. An analysis of this criterion suggests that its importance is dependent upon the number of different methods that can be used to measure the trait.