×

Semiparametric regression. (English) Zbl 1038.62042

Cambridge Series in Statistical and Probabilistic Mathematics 12. Cambridge: Cambridge University Press (ISBN 0-521-78516-2/pbk). xvi, 386 p. (2003).
The primary aim of this book is to guide researchers needing to flexibly incorporate nonlinear relations into their regression analyses. Almost all existing regression texts treat either parametric or nonparametric regression exclusively. In this book the authors argue that nonparametric regression can be viewed as a relatively simple extension of parametric regression and treat the two together. They refer to this combination as semiparametric regression. The approach to semiparametric regression is based on penalized regression splines and mixed models. Every model in this book is a special case of the linear mixed model or its generalized counterpart. This book is very much problem-driven. Examples from their collaborative research have driven the selection of material and emphases and are used throughout the book. The book is suitable for several audiences.
One audience consists of students or working scientists with only a moderate background in regression, though familiarity with matrix and linear algebra is assumed. Another audience that they are aiming at consists of statistically oriented scientists who have a good working knowledge of linear models and the desire to begin using more flexible semiparametric models. There is enough new material to be of interest even to experts on smoothing, and they are a third possible audience. This book consists of 19 chapters and 3 appendixes.

MSC:

62G08 Nonparametric regression and quantile regression
62J02 General nonlinear regression
62J05 Linear regression; mixed models
62-02 Research exposition (monographs, survey articles) pertaining to statistics
62-01 Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics
62F10 Point estimation

Software:

SemiPar
PDF BibTeX XML Cite
Full Text: DOI