A1148
Title: Optimal invariant tests in an instrumental variables regression with heteroskedastic and autocorrelated
Authors: Mahrad Sharifvaghefi - University of Pittsburgh (United States) [presenting]
Abstract: Model symmetries in the instrumental variable (IV) regression are used to derive an invariant test for the causal structural parameter. Contrary to popular belief, it is shown that there exist model symmetries when equation errors are heteroskedastic and autocorrelated (HAC). The theory is consistent with existing results for the homoskedastic model. These symmetries are used to propose the conditional integrated likelihood (CIL) test for the causality parameter in the over-identified model. Theoretical and numerical findings show that the CIL test performs well compared to other tests in terms of power and implementation. Practitioners use the Anderson-Rubin (AR) test in the just-identified model, and the CIL test in the over-identified model is recommended.
