Support is requested for a Resource Related Research Projet to provide the foundation for continued computer software support to biomedical research. The scientific base of medical research includes biostatistics and biomathematics. We have long established record of providing the benefits of biostatistical and biomathematical research to the research community at large. We wish to continue this research to bring newer and more powerful methods into effective use. We not only propose the needed research but have the vehicle to bring the supporting computer software to the researchers through the BMDP computer programs. Our statistical software group has always had a stimulating effect on the statistical computing community. The scope of the research proposed includes continuing investigation of the needs of the biomedical researcher; development and validation of methodology; research into the utility of various kinds of case study material in improving the quality of BMDP program usage; exploratory program development; and trial application of developing methodologies to real problems. Specific topics to be explored include incomplete data, frequency table analysis, fitting functions defined by differential equations, stepwise selection of models in analysis of variance and covariance, sampled permutation tests, and analysis of the structure of covariance matrices.
A second aim of the proposed project is to support packaging and dissemination of selected programs that are important for only a limited area of research. Such programs are often developed to meet a specific need, in the absence of an incentive for generalizing, packaging, fully documenting and distributing them, these programs are seldom usable beyond their home institutions. The project would provide a vehicle for assisting the developers of such programs in preparing them for distribution.
| Little, R J; Wang, Y (1996) Pattern-mixture models for multivariate incomplete data with covariates. Biometrics 52:98-111 |
| Dorey, F J; Little, R J; Schenker, N (1993) Multiple imputation for threshold-crossing data with interval censoring. Stat Med 12:1589-603 |
| Gornbein, J A; Lazaro, C G; Little, R J (1992) Incomplete data in repeated measures analysis. Stat Methods Med Res 1:275-95 |
| Weiss, R E; Lazaro, C G (1992) Residual plots for repeated measures. Stat Med 11:115-24 |
| Rubin, D B; Schenker, N (1991) Multiple imputation in health-care databases: an overview and some applications. Stat Med 10:585-98 |
| Schluchter, M D (1988) Analysis of incomplete multivariate data using linear models with structured covariance matrices. Stat Med 7:317-24 |
| Berk, K (1987) Computing for incomplete repeated measures. Biometrics 43:385-98 |
