Variance Component Testing in Multilevel Models

by: Johannes Berkhof, Tom A Snijders

JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS, Vol. 26, No. 2. (1 January 2001), pp. 133-152.

View FullText article

DOI, HighWire

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

plm, ctacmo, Biostatistics (group), Statistics_and_Social_Science (group)

Find related articles with these CiteULike tags

boundary, component, multilevel, random, variance, variance_components

Abstract

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. 10.3102/10769986026002133

@article{berkhof:snijders:2001, abstract = {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. 10.3102/10769986026002133}, author = {Berkhof, Johannes and Snijders, Tom A. }, citeulike-article-id = {2649190}, doi = {http://dx.doi.org/10.3102/10769986026002133}, journal = {JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS}, keywords = {boundary, variance\_components}, month = {January}, number = {2}, pages = {133--152}, posted-at = {2008-08-29 14:55:58}, priority = {2}, title = {Variance Component Testing in Multilevel Models}, url = {http://dx.doi.org/10.3102/10769986026002133}, volume = {26}, year = {2001} }

RIS record

TY - JOUR ID - berkhof:snijders:2001 L3 - citeulike-article-id:2649190 N2 - 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. 10.3102/10769986026002133 IS - 2 JF - JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS EP - 152 TI - Variance Component Testing in Multilevel Models VL - 26 SP - 133 KW - boundary KW - variance_components AU - Berkhof, Johannes AU - Snijders, Tom PY - 2001/01/01/ UR - http://dx.doi.org/10.3102/10769986026002133 ER -

RIS BibTeX