Controlling for Family Variables in Abuse Effects Research

Abstract

The present article offers a critique of the semipartial correlation approach to abuse effects research. This procedure attempts to “control” statistically for the potentially confounding effects of family environment in the relationship between child abuse and later psychological symptomatology. Unfortunately, the use of such statistics in abuse research may be problematic, especially when control, predictor, and criterion variables are significantly intercorrelated (multicolinear) and the intent is to determine the relative importance of abuse to later psychological functioning. Other problems discussed include the effects of (a) small sample sizes, (b) unreliability of the control variable, (c) ambiguity regarding the causal relationship between control and predictor variables, and (d) theoretical problems inherent in considering abuse “minus” family dysfunction. It is suggested that semipartial correlation analysis can be a highly conservative test of the “abuse effects” hypothesis.