The Department of Statistics at Colorado State University will purchase a central server and two workstations dedicated to support research in time series analysis, statistical inference, and statistical computing. The equipment will be used for several research projects including those described below. 1. Multivariate times series modelling using state-space techniques. 2. Automatic data-driven bandwidth selection criteria will be evaluated in the multivariate setting. 3. Confidence interval procedures for various functions of variances in unbalanced variance components models will be studied. 4. Distribution-free inference procedures in the linear model framework using permutation methods will be investigated. A key component of this investigation will be the development of a permutation package containing numerical and graphical descriptive tools for implementing permutation methods for a broad class of problems.
