| ¡@¡@Two tests, one parametric and the other semiparametric, are proposed for testing bias of estimating equations in weighted regression with partially missing covariates when primary regression model is correctly specified. More generally, the tests may be thought of as a diagnostic tool for the combined package of the primary regression model and the missingness assumptions. The asymptotic null distributions of the two test statistics are derived under the assumption of missingness at random for the partially missing covariates. A small scale simulation study is also illustrated. |