Ignorable and Nonignorable Modeling in Regression with Incomplete Covariates.
Ignorable and Nonignorable Modeling in Regression with Incomplete Covariates.
We consider the regression of outcome Y on regressors W and Z with some values of W missing, when our main interest is the effect of Z on Y, controlling for W. Three common approaches to regression with missing covariates are (a) complete-case analysis (CC), which discards the incomplete cases, …