Statistical Methods for Epidemiological Research

Child Health And Human Development

Investigators

Linked publications & trials

Abstract

To evaluate the risk associated with health outcomes; biomarkers of exposures are commonly obtained in epidemiological studies. However, mixed results have been obtained from these studies. One possible explanation for the mixed results is the methodological challenges that epidemiologist face when analyzing exposures. These include among others, dealing with a large number of observed exposures being below the level of detection (LOD) and imputation methods (i.e imputing zero for values bellow the LOD, etc.), and proper causal modeling, including adjustment for possible confounders (i.e. lipid adjustment vs standardization). We are developing methods to deal with some of these issues.