On the power of tests for superexogeneity and structural invariance

This paper examines the finite-sample power of tests of structural invariance and superexogeneity hypotheses in econometric models with contemporaneous conditioning variables. We consider both direct parametric tests of superexogeneity, as well as indirect procedures based on temporal stability tests for the parameters of interest. Our Monte Carlo analysis reveals that both types of tests may lack power in interesting classes of models. An empirical illustration investigates the superexogeneity of the short-term interest rate in a dynamic specification for the U.S. term structure.