Today's courses in statistical methods, for the most part, focus on the same methods that were taught 30 years ago, before the use of computers became standard in the classroom. The actual practice of statistics has, of course, moved beyond these traditional statistical methods. Modern methods include dynamic computer graphics, nonlinear estimation of various types, spectral analysis, neural networks, resampling, and other simulation-based inference methods. Although these modern methods are often computatiollally demanding, today's computers make their use feasible, if not easy, to perform. Many scientists and engineers use these modern statistical methods routinely. As a result, current statistical methods courses are often viewed, from the outside, as being somewhat outdated. This project develops a collection of instructional modules, built around actual applications from science and engineering. These modules are self-contained with a minimum prerequisite of a first course in statistical methods. They illustrate an appropriate modeling and inferential approach for the problem and illustrate the appropriate application of some of these newly developed and developing statistical methods. The modules include all necessary instructional materials including objectives, examples, lecture materials, computer implementation of the methodology, homework class/discussion exercises, and laboratory assignments to test students' knowledge of basic material and reinforce important conceptual ideas. These modules make it easy for instructors to experiment with and explore the use of modern statistical methodology in undergraduate statistics methods courses. *
