Model checks for regression: An innovation process approach

	Model checks for regression: An innovation process approach
	Stute, W ; Thies, S ; Zhu, LX
刊名	ANNALS OF STATISTICS
	1998-10-01
卷号	26 期号:5 页码:1916-1934
关键词	residual cusum process innovation process goodness-of-fit tests
ISSN号	0090-5364
英文摘要	In the context of regression analysis it is known that the residual cusum process may serve as a basis for the construction of various omnibus, smooth and directional goodness-of-fit tests. Since a deeper analysis requires the decomposition of the cusums into their principal components and this is difficult to obtain, we propose to replace this process by its innovation martingale. It turns out that the resulting tests are (asymptotically) distribution free under composite null models and may be readily performed. A simulation study is included which indicates that the distributional approximations already work for small to moderate sample sizes.
WOS研究方向	Mathematics
语种	英语
出版者	INST MATHEMATICAL STATISTICS
WOS记录号	WOS:000079135700012
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/13385]
专题	中国科学院数学与系统科学研究院
通讯作者	Stute, W
作者单位	1.Univ Giessen, Inst Math, D-35392 Giessen, Germany 2.Chinese Acad Sci, Inst Appl Math, Beijing 100080, Peoples R China
推荐引用方式 GB/T 7714	Stute, W,Thies, S,Zhu, LX. Model checks for regression: An innovation process approach[J]. ANNALS OF STATISTICS,1998,26(5):1916-1934.
APA	Stute, W,Thies, S,&Zhu, LX.(1998).Model checks for regression: An innovation process approach.ANNALS OF STATISTICS,26(5),1916-1934.
MLA	Stute, W,et al."Model checks for regression: An innovation process approach".ANNALS OF STATISTICS 26.5(1998):1916-1934.