Finite Population Correction for Two-Level Hierarchical Linear Modeling

• In Event: 65.060 - Multilevel Modeling: Nonnested Multilevel Data, Measurement Invariance, and Bayesian Approaches

Abstract

The research literature has given little attention to the issue of finite population in hierarchical linear modeling. When the finite population is incorrectly assumed as infinite, the standard errors of the fixed effects are overestimated. In this study, we derive correction formulae for the standard errors of level-1 and level-2 fixed effects in two-level hierarchical linear models. The impact of ignoring finite population correction is illustrated using a simulation study. We encourage researchers to consider the characteristics of the target population, and apply appropriate corrections when needed.

Authors

• Hok Chio (Mark) Lai, University of Cincinnati

• Oiman Kwok, Texas A&M University - College Station

• Yu-Yu Hsiao, Texas A&M University - College Station

• Qian Cao, Texas A&M University - College Station