Abstract
This is a survey of modern developments in statistical regression, written for the mathematically educated nonstatistician. It begins with a review of the traditional theory of least-squares curve-fitting. Modern developments in regression theory have developed in response to the practical limitations of the least-squares approach. Recent progress has been made feasible by the electronic computer, which frees statisticians from the confines of mathematical tractability. Topics discussed include robust regression, bootstrap measures of variability, local smoothing and cross-validation, projection pursuit, Mallows’ $C_p $ criterion, Stein estimation, generalized regression for Poisson data, and regression methods for censored data. All of the methods are illustrated with real-life examples.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call