Computation, Bayesian Methods, Design Fill May Issue

摘要

The May issue covers a number of top-ics with emphasis on computationally intensive methods, Bayesian methods, and design of experiments. In the lead article, "Tuning Variable Selection Procedures by Adding Noise," Xiaohui Luo, Leonard A. Stefanski, and Dennis D. Boos propose a general strategy for adapting variable selection tuning parameters that effectively estimates the tuning parameters so that the selection method avoids over fitting and under fitting. The strategy is based on the principle that under fitting and over fitting can be observed direcdy in estimates of the error variance after adding controEed amounts of additional independent noise to the response variable and then running a variable selection method. It is related to the simulation technique SIMEX, found in the measurement error literature.