Structural change tests for GEL criteria

This paper examines structural change tests based on generalized empirical likelihood methods in the time series context. Standard structural change tests for GMM with strongly identified parameters are adapted to the GEL context. We show that when moment conditions are properly smoothed, these test statistics converge to the same asymptotic distribution as in GMM, in cases with known and unknown breakpoints. New test statistics specific to GEL methods are also introduced. Finally, we propose stability tests in the GEL framework that are robust to weak identification and dependent data. A simulation study examines the small sample properties of the tests.