Locally most powerful tests for spatial interactions in the simultaneous SAR Tobit model

The simultaneous SAR Tobit model is useful to analyze censored data in a spatial or social interaction setting. This paper focuses on three classical tests of spatial interactions in the simultaneous SAR Tobit model. We derive the asymptotic distributions of those three tests under the null and the local alternative hypotheses, establish their asymptotic equivalence and local efficiency, and study finite sample properties by the Monte Carlo simulation. The tests are applied to an empirical example on the presence of competition among school districts on school district income tax in Iowa.

► We derive Wald and LR tests for the simultaneous SAR Tobit model. ► We establish the asymptotic equivalence and local efficiency of classical tests. ► We use Monte Carlo studies to investigate finite sample properties of the tests. ► The tests indicate the existence of tax competition among Iowa school districts.