Oracle Efficient Estimation of Structural Breaks in Cointegrating Regressions

In this article, we propose an adaptive group lasso procedure to efficiently estimate structural breaks in cointegrating regressions. It is well known that the estimator not simultaneously estimation consistent and model selection break settings. Hence, use a first step of diverging number breakpoint candidates produce weights for second estimation. We prove parameter changes are estimated consistently by show greater than true but still sufficiently close it. Then, these results has oracle properties if obtained from our Simulation proposed delivers expected results. An economic application long-run US money demand function demonstrates practical importance methodology.