Optimal changepoint tests for normal linear regression

被引:129
作者
Andrews, DWK
Lee, I
Ploberger, W
机构
[1] KOREA TAX INST,SEOUL,SOUTH KOREA
[2] VIENNA TECH UNIV,VIENNA,AUSTRIA
基金
美国国家科学基金会;
关键词
changepoint test; linear regression; multiple changepoints; optimal test; structural change test;
D O I
10.1016/0304-4076(94)01682-8
中图分类号
F [经济];
学科分类号
02 ;
摘要
This paper determines a class of finite-sample optimal tests for the existence of a changepoint at an unknown time in a normal linear multiple regression model with known variance. Optimal tests for multiple changepoints are also derived. It is shown that the results cover some models of cointegration. Power comparisons of several tests are provided based on simulations.
引用
收藏
页码:9 / 38
页数:30
相关论文
共 23 条
[1]   OPTIMAL TESTS WHEN A NUISANCE PARAMETER IS PRESENT ONLY UNDER THE ALTERNATIVE [J].
ANDREWS, DWK ;
PLOBERGER, W .
ECONOMETRICA, 1994, 62 (06) :1383-1414
[2]   TESTS FOR PARAMETER INSTABILITY AND STRUCTURAL-CHANGE WITH UNKNOWN CHANGE-POINT [J].
ANDREWS, DWK .
ECONOMETRICA, 1993, 61 (04) :821-856
[3]   BEST MEDIAN-UNBIASED ESTIMATION IN LINEAR-REGRESSION WITH BOUNDED ASYMMETRIC LOSS FUNCTIONS [J].
ANDREWS, DWK ;
PHILLIPS, PCB .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1987, 82 (399) :886-893
[4]  
ANDREWS DWK, 1995, IN PRESS ANN STATIST, V23
[5]  
BROWN RL, 1975, J ROY STAT SOC B MET, V37, P149
[6]   ESTIMATING CURRENT MEAN OF NORMAL-DISTRIBUTION WHICH IS SUBJECTED TO CHANGES IN TIME [J].
CHERNOFF, H ;
ZACKS, S .
ANNALS OF MATHEMATICAL STATISTICS, 1964, 35 (03) :999-&
[7]   HYPOTHESIS TESTING WHEN A NUISANCE PARAMETER IS PRESENT ONLY UNDER ALTERNATIVE [J].
DAVIES, RB .
BIOMETRIKA, 1977, 64 (02) :247-254
[8]  
DAVIES RB, 1987, BIOMETRIKA, V74, P33, DOI 10.2307/2336019
[9]   TEST FOR A SHIFTING SLOPE COEFFICIENT IN A LINEAR MODEL [J].
FARLEY, JU ;
HINICH, MJ .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1970, 65 (331) :1320-&
[10]   ON DETECTING CHANGES IN MEAN OF NORMAL VARIATES [J].
GARDNER, LA .
ANNALS OF MATHEMATICAL STATISTICS, 1969, 40 (01) :116-&