Alternative estimators for factor garch models—A monte carlo comparison
Article first published online: 7 NOV 2006
Copyright © 1992 John Wiley & Sons, Ltd.
Journal of Applied Econometrics
Volume 7, Issue 3, pages 259–279, July/September 1992
How to Cite
Lin, W.-L. (1992), Alternative estimators for factor garch models—A monte carlo comparison. J. Appl. Econ., 7: 259–279. doi: 10.1002/jae.3950070304
- Issue published online: 7 NOV 2006
- Article first published online: 7 NOV 2006
- Manuscript Revised: MAR 1992
- Manuscript Received: DEC 1989
This paper proposes four estimators for factor GARCH models: two-stage univariate GARCH (2SUE), two-stage quasi-maximum likelihood (2SML), quasi-maximum likelihood with known factor weights (RMLE), quasi-maximum likelihood with unknown factor weights (MLE). A Monte-Carlo study is designed for bivariate one-factor GARCH models to examine the finite sample properties. Results are presented for biases, ratios of standard errors to standard deviations, ratios of variances, coverage of confidence intervals, effects of misspecified factor weights, and finite sample properties of the 2SUE for factor GARCH-in-mean models.