The Future of Statistical Computing

Abstract

This article forecasts the path of statistical computing in the next decade. Its premise is that technology will influence statistical computing more than other factors. This forecast is based on contemporary observations of the field over the last 40 years and on a supposition that extrapolating these trends is not unreasonable. The technology driving this forecast includes not only hardware, but also the software that provides the infrastructure for individual and community interaction with computers. We should not be surprised to see a proliferation of intelligent data analysis systems embedded in everyday objects and Web sites; automated visualizations for data discovery; analytic systems that are accessible by nonstatisticians (a trend toward simplicity and away from comprehensiveness); distributed analytic systems that talk to each other, fuse disparate data in real time, and draw conclusions on the evidence; and communities of open-source developers exceeding the scope and capabilities of commercial companies. Whether computer scientists eventually take over this field will depend on how actively statisticians participate. Statisticians interested in statistical computing and its future incarnations will have to engage in joint research with computer scientists to continue to have an influence.