Improved statistical analyses of diverse populations

University Of Pennsylvania, Philadelphia PA

Investigators

Linked publications & trials

Abstract

Community based interventions can reduce the risk and overall mortality and morbidity of diseases such as coronary heart disease (CHD) and cancer. They are especially important for African Americans, who are at increased risk for a wide range of negative health conditions, including obesity and obesity related diseases. This pilot study will develop more efficient methods for analysis of longitudinal studies using generalized estimating equation methodology. It will strengthen our foundation for a full research program to improve understanding from longitudinal studies in diverse populations, through improved analytic techniques. Our primary aims are to: (1) To develop more efficient and informative methods for analysis in longitudinal studies and community-based interventions, by developing guidelines for selecting the most appropriate correlation structure when implementing generalized estimating equations (GEE) and GEE based methodology. (2) To apply our methods in analyses of several studies in African-American Populations at the University of Pennsylvania, to further refine and tailor their development to the characteristics of data for diverse populations and to answer new questions that our methods make possible. (3) To compare and contrast our approaches with methods based on random effects models, via simulations and data analyses.