Advanced Linear Modeling: Statistical Learning and Dependent Data

ISBN-13: 9783030291662 / Angielski / Miękka / 2021 / 608 str.

Ronald Christensen

Recenzje

"This book is in my opinion a very valuable resource for researchers since it presents the theoretical foundations of linear models in a unified way while discussing a number of applications. ... This book is definitely worth considering for anyone looking for an extensive and thorough treatment of advanced topics in linear modeling." (Fabio Mainardi, MAA Reviews, May 23, 2021)

O autorze

Ronald Christensen is a Professor of Statistics at the University of New Mexico, Fellow of the American Statistical Association (ASA) and the Institute of Mathematical Statistics, former Chair of the ASA Section on Bayesian Statistical Science and former Editor of The American Statistician. His book publications include Plane Answers to Complex Questions (Springer 2011), Log-Linear Models and Logistic Regression (Springer 1997), Analysis of Variance, Design, and Regression (1996, 2016), and  Bayesian Ideas and Data Analysis (2010, with Johnson, Branscum and Hanson).

Blurb

Now in its third edition, this companion volume to Ronald Christensen’s Plane Answers to Complex Questions uses three fundamental concepts from standard linear model theory—best linear prediction, projections, and Mahalanobis distance— to extend standard linear modeling into the realms of Statistical Learning and Dependent Data.  

This new edition features a wealth of new and revised content.  In Statistical Learning it delves into nonparametric regression, penalized estimation (regularization), reproducing kernel Hilbert spaces, the kernel trick, and support vector machines.  For Dependent Data it uses linear model theory to examine general linear models, linear mixed models, time series, spatial data, (generalized) multivariate linear models, discrimination, and dimension reduction.  While numerous references to Plane Answers are made throughout the volume, Advanced Linear Modeling can be used on its own given a solid background in linear models.  Accompanying R code for the analyses is available online.