A note on spurious break

被引:15
作者
Bai, JS [1 ]
机构
[1] MIT, Dept Econ, Cambridge, MA 02139 USA
基金
美国国家科学基金会;
关键词
D O I
10.1017/S0266466698145061
中图分类号
F [经济];
学科分类号
02 ;
摘要
When the disturbances of a regression model follow an 1(1) process there is a tendency to estimate a break point in the middle of the sample, even though a break point does not actually exist. In this note, we provide a mathematical proof for this phenomenon.
引用
收藏
页码:663 / 669
页数:7
相关论文
共 9 条
[1]   TESTS FOR PARAMETER INSTABILITY AND STRUCTURAL-CHANGE WITH UNKNOWN CHANGE-POINT [J].
ANDREWS, DWK .
ECONOMETRICA, 1993, 61 (04) :821-856
[2]  
BAI J, 1997, IN PRESS REV EC STUD
[3]  
Bai J., 1996, 9613 MIT DEP EC
[4]   TRENDS VERSUS RANDOM-WALKS IN TIME-SERIES ANALYSIS [J].
DURLAUF, SN ;
PHILLIPS, PCB .
ECONOMETRICA, 1988, 56 (06) :1333-1354
[5]  
Granger C. W., 1974, J. Econom., V2, P111, DOI [10.1002/9780470996249.ch27, 10.1016/0304-4076(74)90034-7, DOI 10.1016/0304-4076(74)90034-7]
[6]   SPURIOUS BREAK [J].
NUNES, LC ;
KUAN, CM ;
NEWBOLD, P .
ECONOMETRIC THEORY, 1995, 11 (04) :736-749
[7]   UNDERSTANDING SPURIOUS REGRESSIONS IN ECONOMETRICS [J].
PHILLIPS, PCB .
JOURNAL OF ECONOMETRICS, 1986, 33 (03) :311-340
[8]  
VOGELSANT TJ, 1994, 9412 CAE CORN U
[9]  
VOGELSANT TJ, 1994, UNPUB TESTING SHIFT