On Small Sample Properties of the Wald, LR and LM Tests in a Linear Model with AR(1) Errors
作者:
Hideo Kozumi,
期刊:
Communications in Statistics - Simulation and Computation
(Taylor Available online 1990)
卷期:
Volume 19,
issue 4
页码: 1361-1375
ISSN:0361-0918
年代: 1990
DOI:10.1080/03610919008812921
出版商: Marcel Dekker, Inc.
关键词: AR(1) errors;linear model;LM test;LR test;restricted estimator;Wald test
数据来源: Taylor
摘要:
When the error terms are autocorrelated, the conventional t-tests for individual regression coefficients mislead us to over-rejection of the null hypothesis. We examine, by Monte Carlo experiments, the small sample properties of the unrestricted estimator ofρand of the estimator ofρrestricted by the null hypothesis. We compare the small sample properties of the Wald, likelihood ratio and Lagrange multiplier test statistics for individual regression coefficients. It is shown that when the null hypothesis is true, the unrestricted estimator ofρis biased. It is also shown that the Lagrange multiplier test using the maximum likelihood estimator ofρperforms better than the Wald and likelihood ratio tests.
点击下载:
PDF (316KB)
返 回