Spurious regressions with stationary series

被引:100
作者
Granger, CWJ [1 ]
Hyung, N [1 ]
Jeon, Y [1 ]
机构
[1] Univ Calif San Diego, Dept Econ, La Jolla, CA 92093 USA
关键词
D O I
10.1080/00036840152022232
中图分类号
F [经济];
学科分类号
02 ;
摘要
A spurious regression occurs when a pair of independent series, but with strong temporal properties, are found apparently to be related according to standard inference in an OLS regression. Although this is well known to occur with pairs of independent unit root processes, this paper finds evidence that similar results are found with positively autocorrelated autoregressive series or long moving averages. This occurs regardless of the sample size and for various distributions of the error terms.
引用
收藏
页码:899 / 904
页数:6
相关论文
共 7 条
[1]  
[Anonymous], 1974, J. Econom., DOI [DOI 10.1016/0304-4076(74)90034-7, 10.1002/9780470996249.ch27]
[2]   An introduction to stochastic unit-root processes [J].
Granger, CWJ ;
Swanson, NR .
JOURNAL OF ECONOMETRICS, 1997, 80 (01) :35-62
[4]  
Marmol F, 1996, OXFORD B ECON STAT, V58, P525
[5]   A SIMPLE, POSITIVE SEMIDEFINITE, HETEROSKEDASTICITY AND AUTOCORRELATION CONSISTENT COVARIANCE-MATRIX [J].
NEWEY, WK ;
WEST, KD .
ECONOMETRICA, 1987, 55 (03) :703-708
[6]   UNDERSTANDING SPURIOUS REGRESSIONS IN ECONOMETRICS [J].
PHILLIPS, PCB .
JOURNAL OF ECONOMETRICS, 1986, 33 (03) :311-340
[7]   Why do we sometimes get nonsense-correlations between time-series? - A study in sampling and the nature of time-series. [J].
Yule, GU .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY, 1926, 89 :1-69