Fitting multilevel models in complex survey data with design weights: Recommendations
Department of Psychology, University of North Florida, 1 UNF Drive, Jacksonville, FL, 32224, USA
BMC Medical Research Methodology 2009, 9:49 doi:10.1186/1471-2288-9-49Published: 14 July 2009
Multilevel models (MLM) offer complex survey data analysts a unique approach to understanding individual and contextual determinants of public health. However, little summarized guidance exists with regard to fitting MLM in complex survey data with design weights. Simulation work suggests that analysts should scale design weights using two methods and fit the MLM using unweighted and scaled-weighted data. This article examines the performance of scaled-weighted and unweighted analyses across a variety of MLM and software programs.
Using data from the 2005–2006 National Survey of Children with Special Health Care Needs (NS-CSHCN: n = 40,723) that collected data from children clustered within states, I examine the performance of scaling methods across outcome type (categorical vs. continuous), model type (level-1, level-2, or combined), and software (Mplus, MLwiN, and GLLAMM).
Scaled weighted estimates and standard errors differed slightly from unweighted analyses, agreeing more with each other than with unweighted analyses. However, observed differences were minimal and did not lead to different inferential conclusions. Likewise, results demonstrated minimal differences across software programs, increasing confidence in results and inferential conclusions independent of software choice.
If including design weights in MLM, analysts should scale the weights and use software that properly includes the scaled weights in the estimation.