Doing research the hard way: Substituting analysis of variance for a problem in correlational analysis

    loading  Checking for direct PDF access through Ovid


In a recent publication, J. R. Kirby and J. P. Das (see PA, 62:5150) dichotomized 2 measures of individual differences at medians and thereafter treated these measures as if they were independent variables in an ANOVA. If instead they had analyzed their various measures by means of traditional correlational analysis, they would have had much more powerful tests of their hypotheses. They would also, in all probability, have been less inclined to interpret their results as if the dichotomized variables represented independent, causal antecedents of their various measures of intelligence. (4 ref) (PsycINFO Database Record (c) 2006 APA, all rights reserved)

Related Topics

    loading  Loading Related Articles