A Note on Missing Data Effects on the Hausman (1978) Simultaneity Test: Some Monte Carlo Results.

This short paper demonstrates the effects of using missing data on the power of the well-known Hausman (1978) test for simultaneity in structural econometric models. This test is a reliable test and is widely used for testing simultaneity in linear and nonlinear structural models. Using Monte Carlo techniques, we find that the existence of missing data could affect seriously the power of the test. As their number is getting larger, the probability of rejecting simultaneity with Hausman test is increasing significantly especially in small samples. A Full Information Maximum Likelihood Missing Data correction technique is used to overcome the problem and then we find out that that the test is more effective when we retrieve these data and include them in the sample.