Skip to main content
SLU publication database (SLUpub)

Research article2003

Quasi-Maximum Likelihood Estimators in GARCH(1,2) Model: Asymptotics and Applications

Yingfu Xie, Yu Jun

Abstract

In this paper, we investigate the asymptotic properties of the quasi-maximum likelihood estimator (quasi-MLE) for GARCH(1,2) model. Consistency of the global quasi-MLE and asymptotic normality of the local quasi-MLE are obtained, which extend the results in Lee and Hansen (1994) for GARCH(1,1). Two sets of financial data, stock returns in Standard and Poor's 500 Index and Shanghai Stock Exchange Index, are analyzed as applications. It is shown that more complicated models than GARCH(1,1) for describing the variance process are needed for daily data

Keywords

GARCH; quasi-maximum likehood estimator; consistency; asymptotic normality; S&P 500; SEE

Published in

Research report (Centre of Biostochastics)
2003, Volume: 2003, number: 5, pages: 1-28 Publisher: SLU