This project addresses statistical problems generated from collaboration with scientists in other program areas and general statistical problems of current interest. This project is a continuing activity of the Section on Mathematical Statistics and other members of the branch. Papers have been submitted, are in review or were published in FY 1991 on the following statistical subjects: evaluation of exact likelihood estimation of parameters in a Markov mixture model; development of validation methods for screening instruments used in surveys of diseases with low prevalence; assessment of national prevalence estimates of a disease obtained by adjusting previous estimates and incorporating estimates from independent community-based surveys; development of a Wiebull model for survival data with dependent censoring; an empirical Bayes procedure for examining the relationships between multiple time series; establishing statistical quality control methods for biomedical laboratories; design of panel studies under alternating Poisson process assumptions. Other work in progress includes: selection criteria for use of the Kaplan-Meier or parametric MLE for survival analysis; influence of missing data in randomized clinical trials; methods to improve coverage in surveys; estimation of time-to-event data in the presence of left-and right-censoring; site selection for epidemiologic surveys,, adjustments for covariates in the analysis of categorical data; two-state models for analyzing time series count data; analysis of response surface data with both spatial and temporal components; development of sampling strategies for count data in the presence of multiple types of clustering; development of statistical models and analysis methods for time series of ordinal data; modeling of response surfaces with spatially correlated errors; application of splines to estimate model parameters of multiple correlated response surfaces; and combining information from negatively correlated nonlinear regressions.
