Testing Structural Change in Conditional Distributions via Quantile Regressions

We propose tests for structural change in conditional distributions via quantile regressions. To avoid misspecification on the conditioning relationship, we construct the tests based on the residuals from local polynomial quantile regressions. In particular, the tests are based upon the cumulative sums of generalized residuals from quantile regressions and have power against local alternatives at rate n−1/2. We derive the limiting distributions for our tests under the null hypothesis of no structural change and a sequence of local alternatives. The proposed tests apply to a wide range of dynamic models, including time series regressions with m.d.s. errors, as well as models with serially correlated errors. To deal with possible correlations in the error process, we also propose a simulation method to obtain the p-values for our tests. Finally, Monte Carlo simulations suggest that our tests behave well in finite samples. JEL classifications: C12, C14, C22, C5