EFFECT OF MISSING AN INFLUENTIAL COVARIATE

Abstract
It is well known that while considering relationship between a response variate Yand an auxiliary variate X, if another important covariate Zis ignored, we may get into a paradoxical situation. One such example is Simpson's paradox. In this paper, we investigate the extent of effect of ignoring an important covariate Zon the relationship between the response variate Yand the auxiliary variate X. The relationship between these variates is modelled by logistic regression model and Cox regression model.