Regression Based Causal Induction with Latent Variable Models

Abstract

4> fi Y X measures the expected change in Y produced by a unit change in X with all other predictor variables held constant. Regression models include variables for which fi is large. Descriptions of regression methods can be found in any standard regression text [3]. It is widely believed that regression is ill-suited to the task of causal induction. Arguments against using regression methods rest on the fact that the error in estimating fi Y X can be quite large, particularly when unmeasured or latent variables account for the relationship between X and Y , or when X is a common cause of Y and another predictor [5,7]. In fact, fi may suggest X has a strong influence on Y when it has little or none. We have developed a regression-based causal induction algorithm called FBD [1] which pe