學 術 演 講
學 術 演 講
題 目：Estimation of Threshold Boundary Regression Models
時 間：民國112年3月13日 (星期一) 上午10：00
This talk considers the threshold boundary regression (TBR) model for sample splitting. The TBR model accommodates covariates in both the regression and threshold functions. The threshold function is allowed to be a nonlinear function of multiple covariates, constituting a hyperplane to describe data dynamics in two different states. We propose TBR-WSVM, a two-stage method that incorporates the weighted support vector machine (WSVM) and least-squares (LS) methods to estimate the TBR model. Under regularity conditions, we evaluate the consistency of the TBR-WSVM estimators with their optimal convergence rates. We conduct several simulation experiments to investigate the finite sample performance of the TBR-WSVM estimator. Compared with two recently proposed methods, TBR-WSVM enjoys three advantages: (i) threshold parameters need not be prefixed with nonzero values, (ii) threshold parameter ranges need not be specified, and (iii) the threshold boundary can be non-linearly estimated. Finally, we apply the TBR model to a real data analysis.Keywords：consistency; least-squares method; support vector machine; threshold model.