NBER-NSF Time Series Conference; University of California at Davis, USA
 

Abstract for "On parameter estimations of threshold autoregressive models" by Ngai Hang CHAN

This paper studies the threshold estimation of a TAR model when the underlying threshold parameter is a random variable. It is shown that the Bayesian estimator is consistent and its limit distribution is expressed in terms of a limit likelihood ratio. Furthermore, convergence of moments of the estimators is also established. To achieve the goal, a continuous-time version of this model is discussed and the properties of the maximum likelihood estimators and the Bayesian estimators are developed. The limit distribution can be computed via explicit simulations from which testing and inference for the threshold parameter can be conducted. The obtained results are illustrated with numerical simulations.

Sponsors: