An investigation of an unbiased correction for heteroskedasticity and the effects of misspecifying the skedastic function

被引:4
作者
Belsley, DA [1 ]
机构
[1] Boston Coll, Dept Econ, Chestnut Hill, MA 02467 USA
关键词
D O I
10.1016/S0165-1889(01)00076-8
中图分类号
F [经济];
学科分类号
02 ;
摘要
The traditional three-step procedure for correcting for heteroskedasticity uses a consistent but biased estimator for the variances sigma(t)(2) in enacting the second step. An estimator is developed here that is unbiased in the presence of heteroskedasticity. Its behavior is examined along with the traditional estimator and another known to be unbiased in the absence of heteroskedasticity. The behavior of these corrective methods is also examined when the form and arguments of the skedastic function are misspecified. This is accomplished using Monte Carlo studies of several situations of interest. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:1379 / 1396
页数:18
相关论文
共 6 条
[1]   SIMPLE TEST FOR HETEROSCEDASTICITY AND RANDOM COEFFICIENT VARIATION [J].
BREUSCH, TS ;
PAGAN, AR .
ECONOMETRICA, 1979, 47 (05) :1287-1294
[2]  
Davidson R., 1993, ESTIMATION INFERENCE, DOI DOI 10.1017/S0266466600009452
[3]   A NEW TEST FOR HETEROSKEDASTICITY [J].
GLEJSER, H .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1969, 64 (325) :316-&
[4]   SOME TESTS FOR HOMOSCEDASTICITY [J].
GOLDFELD, SM ;
QUANDT, RE .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1965, 60 (310) :539-547
[5]  
MACKINNON JG, 1992, J ECON LIT, V30, P102
[6]  
Pindyck R.S., 1998, ECONOMETRIC MODELS E