BOOTSTRAP TESTS FOR GENERALIZED LEAST-SQUARES REGRESSION-MODELS

被引:2
作者
RAYNER, RK
机构
[1] Penn State Erie, Erie
关键词
D O I
10.1016/0165-1765(90)90128-N
中图分类号
F [经济];
学科分类号
02 ;
摘要
This paper shows that certain statistics in the normal linear regression model may be bootstrapped to obtain test procedures with faster rates of convergence than the usual normal approximation. Specifically, bootstrapping a standardized estimator of the regression coefficients is shown to produce errors with smaller order than n-1, and bootstrapping a variance-adjusted statistic gives errors of smaller order than n-2. An advantage of the bootstrap is that it provides an additional step in asymptotic accuracy without the necessity of explicitly calculating correction terms. © 1990.
引用
收藏
页码:261 / 265
页数:5
相关论文
共 8 条
[2]   1977 RIETZ LECTURE - BOOTSTRAP METHODS - ANOTHER LOOK AT THE JACKKNIFE [J].
EFRON, B .
ANNALS OF STATISTICS, 1979, 7 (01) :1-26
[3]   ON THE BOOTSTRAP AND CONFIDENCE-INTERVALS [J].
HALL, P .
ANNALS OF STATISTICS, 1986, 14 (04) :1431-1452
[4]   THEORETICAL COMPARISON OF BOOTSTRAP CONFIDENCE-INTERVALS [J].
HALL, P .
ANNALS OF STATISTICS, 1988, 16 (03) :927-953
[5]  
RAYNER RK, 1989, IN PRESS EC LETT
[6]  
RAYNER RK, 1988, UNPUB BOOTSTRAPPING
[7]  
Rothenberg T. J., 1984, HDB ECONOMETRICS, V2
[8]   APPROXIMATE NORMALITY OF GENERALIZED LEAST-SQUARES ESTIMATES [J].
ROTHENBERG, TJ .
ECONOMETRICA, 1984, 52 (04) :811-825