Intraclass Correlation Values for Planning Group-Randomized Trials in Education

Experiments that assign intact groups to treatment conditions are increasingly common in social research. In educational research, the groups assigned are often schools. The design of grouprandomized experiments requires knowledge of the intraclass correlation structure to compute statistical power...

Full description

Saved in:
Bibliographic Details
Published in:Educational evaluation and policy analysis 2007-03, Vol.29 (1), p.60-87
Main Authors: Hedges, Larry V., Hedberg, E. C.
Format: Article
Language:English
Subjects:
Academic Achievement
Base year
Comprehensive Tests of Basic Skills
Correlation
Correlations
Demography
Design of experiments
Early Childhood Longitudinal Survey
Education
Educational Research
Effect Size
Elementary Secondary Education
Estimates
Experiments
Intervention
Intraclass Correlation
Longitudinal studies
Low Achievement
Mathematical models
Mathematics Achievement
Mathematics Tests
Medical treatment
Pretests
Pretests Posttests
Probability
Public health
Reading Achievement
Reading Tests
Sample Size
Socioeconomic Status
Standard error
Statistical Analysis
Statistical variance
Studies
Urban Schools
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Experiments that assign intact groups to treatment conditions are increasingly common in social research. In educational research, the groups assigned are often schools. The design of grouprandomized experiments requires knowledge of the intraclass correlation structure to compute statistical power and sample sizes required to achieve adequate power This article provides a compilation of intraclass correlation values of academic achievement and related covariate effects that could be used for planning group-randomized experiments in education. It also provides variance component information that is useful in planning experiments involving covariates. The use of these values to compute the statistical power of group-randomized experiments is illustrated.
ISSN:0162-3737
1935-1062
DOI:10.3102/0162373707299706