Multilevel Modeling: A Review of Methodological Issues and Applications

被引:126
作者
Dedrick, Robert F. [1 ]
Ferron, John M.
Hess, Melinda R. [1 ]
Hogarty, Kristine Y. [2 ]
Kromrey, Jeffrey D.
Lang, Thomas R. [3 ]
Niles, John D.
Lee, Reginald S. [4 ]
机构
[1] Univ S Florida, Ctr Res Evaluat Assessment & Measurement, Tampa, FL 33620 USA
[2] Univ S Florida, Coll Educ, Tampa, FL 33620 USA
[3] Univ S Florida, Dept Measurement & Res, Tampa, FL 33620 USA
[4] Univ S Florida, Dept Anthropol, Tampa, FL 33620 USA
关键词
hierarchical modeling; statistics; data analysis; SMALL SAMPLE INFERENCE; MIXED LINEAR-MODEL; COVARIANCE STRUCTURE; MAXIMUM-LIKELIHOOD; MISSING DATA; VARIANCE-COMPONENTS; STANDARD ERRORS; INCOMPLETE DATA; EXACT TESTS; PREDICTION;
D O I
10.3102/0034654308325581
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
This study analyzed the reporting of multilevel modeling applications of a sample of 99 articles from 13 peer-reviewed journals in education and the social sciences. A checklist, derived from the methodological literature oil multilevel modeling and focusing on the issues of model development and specification, data considerations, estimation, and inference, was used to analyze the articles. The most common applications were two-level models where individuals were nested within contexts. Most studies were non-experimental and used nonprobability samples. The amount of data at each level varied widely across studies, as did the number of models examined. Analyses of reporting practices indicated some clear problems, with man v articles riot reporting enough information for a reader to critique the reported analyses. For example, in many articles, one could not determine how many models were estimated, what covariance structure was assumed, what type of centering if any was used, whether the data were consistent with assumptions, whether outliers were present. or how the models were estimated. Guidelines for researchers reporting multilevel analyses are provided.
引用
收藏
页码:69 / 102
页数:34
相关论文
共 90 条