APA Dictionary of Psychology

n. an approach to the statistical control of the influence of a variable or set of variables on other variables of interest (typically, the dependent and independent variables). Partialing helps clarify a specific relationship by excluding the effects of other variables that may also be associated. In a multiple regression model, for example, a researcher may want to remove the effects of a set of covariates before examining the final regression coefficients of interest. Also called partialing out.