Statistical Software for Resampling Methods

RES300 – NIH “Resample II”

Medical data often require complex models. For example, clinical monitoring produces time induced correlation, and relationships among variables change due to medical intervention. Many popularly used biostatistical procedures depend on approximations made for mathematical tractability.

Resampling methods extend the range of classical methods, and have the potential to dramatically affect 21st Century statistics. Resampling methods approximate the distribution of a statistic using only the observed data. The two-fold advantages of resampling methods are that (1) they are conceptually simple and (2) they often apply in complex problems inaccessible through other techniques.

Phase II research will develop algorithms, graphics, and diagnostics for several resampling methods, focusing on the bootstrap. Graphics and a graphical user interface will make the software easy to learn and use. Research will extend and combine efficient computational techniques. The software will support the different needs of (1) data analysts and (2) biostatistical researchers who want to modify resampling capabilities.

S-Plus Resample will enable medical researchers to earn a greater return on their investment of collecting data: achieving reliable inference with computational techniques that are easy to understand and use, yet apply in complex problems in accessible through other methods.