Since many epidemiologic problems cannot be solved by standard tachniques, new methods can help extract more complete answers from research data. The objective of this project is to use mathemticacal theory and computer simulations to develop and evaluate statistical methods appropriate to data arising in epidemiologic research, and to carry out the statistical programming needed to make these methods easily available to other researchers. This may include evaluating outside computer software, using standard programs in novel ways, and writing special purpose programs. Further study will continue in the use of the generalized linear models and the SAS procedure GLM in regression, analysis of variance, and analysis of covariance. Special interest will be paid to the use of logistic regression and log-linear models. Computing techniques such as the linking together of FORTRAN functiosn and SAS procedures will also be explored. Useful techniques will be presented to the branch in seminars, and more comprehensive reports will be submitted to the statistical journals.
