Testing for random coefficient autoregressive and stochastic unit root models

Research output: Contribution to journalArticlepeer-review

Abstract

The random coefficient autoregressive model has been utilized for modeling financial time series because it possesses features that are often observed in financial time series. When the mean of the random coefficient is one, it is called the stochastic unit root model. This paper proposes two Lagrange multiplier tests for the null hypotheses of random coefficient autoregressive and stochastic unit root models against a more general model. We apply our Lagrange multiplier tests to several stock index data, and find that the stochastic unit root model is rejected, whereas the random coefficient autoregressive model is not. This result indicates that it is important to check the validity of the stochastic unit root model prior to applying it to financial time series data, which may be better modeled by the random coefficient autoregressive model with the mean being not equal to one.

Original languageEnglish
Article number20190013
JournalStudies in Nonlinear Dynamics and Econometrics
DOIs
Publication statusAccepted/In press - 2020

Keywords

  • Exact score
  • Lagrange multiplier test
  • Random coefficient autoregressive model
  • State space model
  • Stochastic unit root model

ASJC Scopus subject areas

  • Analysis
  • Social Sciences (miscellaneous)
  • Economics and Econometrics

Fingerprint Dive into the research topics of 'Testing for random coefficient autoregressive and stochastic unit root models'. Together they form a unique fingerprint.

Cite this