|
Roy Whitmore, PhD, senior statistician, joined RTI in 1980. He is an expert in the design and analysis of complex probability samples. His primary areas of application have been human exposure assessment surveys and postsecondary education surveys, for which he has directed sampling design, sample selection, weighting, imputation, and analysis tasks. The environmental surveys are usually stratified, multistage area household surveys because collection of environmental specimens usually requires in-person visits to sample households and sampling at different times because of diurnal and seasonal variations. The postsecondary education surveys usually are stratified, multistage samples selected from lists of postsecondary institutions. For both types of studies, samples usually are selected with probabilities proportional to a composite measure of size to ensure adequate sample sizes for various analysis domains while minimizing variability in person-level probabilities of selection and in the size of the sample selected from primary sampling units. | 