The Effect of a Covariate on Standard Error and Confidence Interval Width

被引：0

作者：

Liu, Xiaofeng ^{[1
]}

机构：

[1] Univ S Carolina, Dept Educ Studies, Columbia, SC 29209 USA

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2011年 / 40卷 / 03期

关键词：

ANCOVA; Covariate imbalance; Sample size; Standard error;

D O I：

10.1080/03610920903391337

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

The standard error of covariate-adjusted mean difference is not always smaller than that of the unadjusted mean difference despite the fact that adding a covariate is commonly believed to reduce the unexplained error variance. The covariate mean difference between the contrasted treatment conditions can inflate the standard error of the adjusted mean difference. If the covariate is viewed as randomly varying from one study to another, a minimum sample size can be found to attain a desired probability of reducing the standard error and the confidence interval width for the adjusted mean difference.

引用

页码：449 / 456

页数：8