Statistical methodology is being applied and developed for longitudinal studies and other studies of aging. The research program focuses on several types of statistical models: 1) longitudinal mixed-effects regression models which consider both within- and between-subject variation in analyzing the repeated measurements for all individuals in the study population, 2) survival analysis for studying risk factors in prospective studies, 3) multiple comparisons for testing group differences in experimental or observational designs, 4) mixture models for describing age changes in distributions of biological markers, and 5) experimental design. Other techniques used include Bayesian, maximum likelihood and numerical computing methods. A major emphasis of the research program is the development of methods which yield cogent yet easily understood results when applied to data. Several mixed-effects longitudinal regression analyses have been completed. An analysis of longitudinal changes in hearing sensitivity in BLSA men and women was the largest mixed-effects analysis ever reported. A method of estimating when an event took place (e.g., first detectable PSA increase from prostate cancer) was developed using a piecewise nonlinear mixed-effects analysis. A new method of examining longitudinal change as a risk factor in survival analysis was developed using a two-stage time-dependent Cox proportional hazards regression approach. The research program has extended earlier methods of longitudinal data analysis, introduced novel methods of describing the natural history of aging, and developed new approaches toward the use of longitudinal data in epidemiological and biomedical studies of aging and associated disease states.
