Paper Summary
Share...

Direct link:

The Impact of Sample Size on Three-Level Cross-Classified Multiple Membership Growth Curve Modeling Estimation

Fri, April 13, 2:15 to 3:45pm, Westin New York at Times Square, Floor: Ninth Floor, Plymouth Room

Abstract

This simulation study examines parameter recovery in three-level cross-classified multiple membership growth curve modeling under a variety of manipulated conditions including: the number of measurement occasions (3 and 5), the number of groups (30, 50, and 100), average group sizes (20 and 40), and multiple membership rate (20% and 40%). Across all conditions investigated in the current study, no substantial relative bias was found for fixed effect estimates, level one variance estimates, or between-student variance in the intercept and slope variance component estimates. However, in some smaller number group conditions (<=50), between-school variance in the intercept, between-first-school variance in the slope, and between-subsequent-school variance in the slope estimates were substantially biased.

Authors