February 7, 2010
The use of multilevel modeling with data from population-based surveys is often limited by the small number of cases per Level 2 unit, prompting a recent trend in the neighborhood literature to apply cluster techniques to address the problem of data sparseness. In this study, the authors use Monte Carlo simulations to investigate the effects of marginal group sizes on multilevel model performance, bias, and efficiency. They then employ cluster analysis techniques to minimize data sparseness and examine the consequences in the simulations. They find that estimates of the fixed effects are robust at the extremes of data sparseness, while cluster analysis is an effective strategy to increase group size and prevent the overestimation of variance components. However,researchers should be cautious about the degree to which they use such clustering techniques due to the introduction of artificial within-group heterogeneity.
Key Words: multilevel models • data sparseness • cluster analysis • Monte Carlo simulations • survey research
February 7, 2010
This article outlines a research strategy for studying difficult-to-reach migrant populations that combines community collaboration, targeted random sampling, and parallel sampling in sending and receiving areas. The authors describe how this methodology was applied to the study of gender, migration, and HIV risks among Hispanic migrants in Durham, North Carolina. They illustrate the usefulness of community collaboration for informing survey design and providing a contextual understanding of research findings. They likewise demonstrate the importance of parallel sampling and assess the bias that would have resulted from conducting their study withconvenience samples as opposed to a targeted random sampling technique. While the authors describe its application to HIV risks among Hispanic migrants, the methodology can easily beextended to other migrant groups as well as to other sensitive topics pertaining to migration and social adaptation.
Key Words: immigrant health • mixed methodology • participatory research • survey research • Mexicans