The Use of Structural Equation Models in Interpreting Regression Equations Including Suppressor and Enhancer Variables

Abstract

It is shown that the usual interpretation of "sup pressor" effects in a multiple regression equation assumes that the correlations among variables have been generated by a particular structural (causal) model, namely, Conger's (1974) two-factor model. A distinction is drawn between the technical definition of "suppression," which is more fittingly labelled enhancement, and suppression as the appropriate interpretation of a regression equation exhibiting enhancement when that equation has been gen erated by the two-factor model. It is demonstrated that a number of models can generate enhancement but cannot sensibly be interpreted in terms of the measuring, removing, or suppressing of irrelevant or invalid variance. How a regression equation is interpreted thus depends critically on the structural model deemed appropriate.

Creativity, mood, and the examined life: Self-reflective rumination boosts creativity, brooding breeds dysphoria.

“…Perhaps this is what we would expect if the correlation were indirect, fueled by two distinct but related types of mminafion (a situation also known as inconsistent mediation; McFatter, 1979). This might also explain why the correlation is stronger in accomplished artists-they might ruminate more often, more deeply, or more uncontrollably, thus putting them at a higher risk of depression.…”

Suppressor Variables in Social Work Research: Ways to Identify in Multiple Regression Models

“…When this situation occurs, researchers often find it difficult to explain the results and tend to regard such variables -with suspicion and distrust‖ (Horst, 1941, p. 435). Thus, a strong temptation exists to eliminate these variables and retain a model that is in line with the researcher's theory and hypothesis (Gelman & Hill, 2007;McFatter, 1979). In reality, such results clearly imply the presence of a suppressor variable, and the negative sign is a result of the suppressor's low correlation with the outcome variable and high correlation with other predictor variables at the bivariate level.…”

Dimensional Model for Estimating Factors influencing Childhood Obesity: Path Analysis Based Modeling

“…The confirmatory factor analysis is used to test the validity and suitability of the indicators for each construct [21]. The outcome from this procedure is the goodness of fit values for each construct.…”