The assistant professor in our school Mr. Cai Biqing’s cooperation paper (collaborators: Jiti Gao at Monash University, Australia; Dag Tj ø stheim at University of Bergen, Norway), "A new class of bivariate threshold cointegration models"was published in the leading journal in the field of econometrics and economics Journal of Business and Economic Statistics, 2017, 2 (Volume 35, Issue 2, Pages 288-305).
In this article, we introduce a new class of bivariate threshold VAR cointegration models. In the models, outside a compact region, the processes are cointegrated, while in the compact region, we allow different kinds of possibilities. We show that the bivariate processes form a 1/2-null recurrent system. We also find that the convergence rate for the estimators for the coefficients in the outside regime is √T, while the convergence rate for the estimators for the coefficients in the middle regime is T 1/4. Moreover, we show that the convergence rate of the cointegrating coefficient is T, which is same as for the linear cointegration model. The Monte Carlo simulation results suggest that the estimators perform reasonably well in finite samples. Applying the proposed model to study the dynamic relationship between the federal funds rate and the 3-month Treasury bill rate, we find that cointegrating coefficients are the same for the two regimes while the short run loading coefficients are different.
β-null recurrent; Cointegration; Markov chain; Threshold VAR models.