This study will develop statistical methods for the analysis of data from complex designed surveys and test them empirically using the National Health and Nutrition Examination Survey I and II (NHANES). Existing multiple linear regression methods for the analysis of data from complex surveys are compared to newly developed regression methods. These regression methods will be applied to the NHANES data sets to determine if they can be used to provide new information on the complex relationships of growth and nutrition. The preliminary results from this research indicate that the newly developed regression models can better describe complex relationships in the data. This research is being pursued in part through a research contract with the Research Triangle Institute to work in collaboration with NICHD to carry out this study. Over the course of this contract, manuscripts will be prepared for publication which will present the results of the study along with the development of computer programs for applying the methods to real data.
