Evaluating Models for Partially Clustered Designs

Partially clustered designs, where clustering occurs in some conditions and not others, are common in psychology, particularly in prevention and intervention trials. This article reports results from a simulation comparing 5 approaches to analyzing partially clustered data, including Type I errors, parameter bias, efficiency, and power. Results indicate that multilevel models adapted for partially clustered data are relatively unbiased and efficient and consistently maintain the nominal Type I error rate when using appropriate degrees of freedom. To attain sufficient power in partially clustered designs, researchers should attend primarily to the number of clusters in the study. An illustration using data from a partially clustered eating disorder prevention trial is provided.