Econometrics of multiple structural changes

ost of the studies in the structural change literature are limited to the case of a single change. My thesis examines some unexplored areas in multiple structural change models. It contains three essays.;The first essay provides a first attempt to examine the consequences of under-specifying the number of change points in structural change models. In contrast to the conventional misspecification analysis, I show that some of the true change points can still be consistently estimated by the misspecified model. The true change points, true structural parameters, and the covariance structure between regressors together determine which change points can be consistently estimated. The theory explains why previous empirical works on estimating the locations of structural changes by using an at-most-one-change model often get desirable results.;The second essay utilizes the results obtained in the first essay to derive a sequential test for the number of change points in structural change models. In the first step, the parameters are estimated by a one-break model, and the null hypothesis that there is no structural break against the alternative that there is one break is tested. If the null is rejected, then the whole sample is split into two subsamples, using the estimated change point in the previous step as a cutoff point. The same procedure is repeated until the null in each sub-sample is accepted. Using this sequential procedure, not only can the number of change points be tested, but their locations can also be consistently estimated.;My third essay develops a comprehensive asymptotic theory for the least squares estimators in an AR(1) model with a single structural break of unknown timing. Let...