Variance component testing in multilevel models

被引：49

作者：

Berkhof, J ^{[1
]}

Snijders, TAB

机构：

[1] Free Univ Amsterdam, Med Ctr, Amsterdam, Netherlands

[2] Univ Groningen, Dept Stat Measurement Theory & Informat Technol, NL-9700 AB Groningen, Netherlands

来源：

JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS | 2001年 / 26卷 / 02期

关键词：

multilevel models; variance components; random coefficients; score tests; Monte Carlo study;

D O I：

10.3102/10769986026002133

中图分类号：

G40 [教育学];

学科分类号：

040101 ; 120403 ;

摘要：

Available variance component tests are reviewed and three new score tests are presented In the first score test, the asymptotic normal distribution of the test statistic is used as a reference distribution. In the other two score tests, a Satterthwaite approximation is used for the null distribution of the test statistic. We evaluate the performance of the score tests and other available tests by means of a Monte Carlo study. The new tests are computationally relatively cheap and have good power properties.

引用

页码：133 / 152

页数：20

共 23 条

[1]

*APT SYST, 1994, GAUSS

[2]

Bryk A.S., 1992, Hierarchical Models: Applications and Data Analysis Methods

[3] Exact tests for variance components [J].