Random Versus Nonrandom Coefficient Models for Multilevel Analysis

Richard L. Tate and Yuwadee Wongbundhit

Journal of Educational and Behavioral Statistics, 1983, vol. 8, issue 2, 103-120

Abstract: It has been argued recently that adequate representation of the multilevel processes of interest in many educational settings will often require models with coefficients that are random rather than nonrandom. Computer simulation results presented here demonstrate the extent to which the two most common multilevel or contextual analysis procedures may mislead when data are, in fact, generated with a random coefficients process. In contrast, correct results are obtained with a third method, which has been recently proposed but not used yet in substantive research.

Keywords: Multilevel analysis; contextual analysis; random coefficients; statistical inference (search for similar items in EconPapers)
Date: 1983
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.3102/10769986008002103 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:jedbes:v:8:y:1983:i:2:p:103-120

DOI: 10.3102/10769986008002103

Access Statistics for this article

More articles in Journal of Educational and Behavioral Statistics
Bibliographic data for series maintained by SAGE Publications ().