Preliminary test of fit in a general class of conditionally heteroscedastic nonlinear time series
- Authors
- Baek, J. S.; Park, J. A.; Hwang, S. Y.
- Issue Date
- May-2012
- Publisher
- TAYLOR & FRANCIS LTD
- Keywords
- conditional heteroscedasticity; nonlinear GARCH; nonlinear time series; preliminary test of fit
- Citation
- JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, v.82, no.5, pp 763 - 781
- Pages
- 19
- Journal Title
- JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
- Volume
- 82
- Number
- 5
- Start Page
- 763
- End Page
- 781
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/12363
- DOI
- 10.1080/00949655.2011.558087
- ISSN
- 0094-9655
1563-5163
- Abstract
- This article is concerned with a general class of conditionally heteroscedastic time series including possibly nonlinear and asymmetric autoregressive conditional heteroscedastic (ARCH) and generalized ARCH models. A problem of preliminary test of fit (PTF, hereafter) within the broad class under consideration is discussed. It is noted that contrary to usual tests in the literature of conditionally heteroscedastic time series, PTF does not require any specification of the conditional variance in advance. Based on the joint limit distributions of sample autocorrelations, a certain Portmanteau-type statistic for PTF is proposed, and its limit is shown to be a chi-square distribution. In addition, some simulation studies, under various innovations, are reported to support our theoretical results.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 이과대학 > 통계학과 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.