ESTIMATION OF A CHANGE-POINT IN MULTIPLE-REGRESSION MODELS

This paper studies the least squares estimation of a change point in m ultiple regressions. Consistency, rate of convergence, and asymptotic distributions are obtained. The model allows for lagged dependent vari ables and trending regressors. The error process can be dependent and heteroskedastic. For nonstationary regressors or disturbances, the asy mptotic distribution is shown to be skewed. The analytical density fun ction and the cumulative distribution function for the general skewed distribution are derived. The analysis applies to both pure and partia l changes. The method is used to analyze the response of market intere st rates to discount rate changes.