A Parametric Approach to Nonparametric Statistics
◆Springer Nature Yellow Sale 開催中!:2024年6月23日(日)ご注文分まで
※上記表示の販売価格は割引適用後の価格です 出版済み 3週間でお届けいたします。 Softcover reprint of the original 1st ed. 2018 Series: Springer Series in the Data Sciences Author: Alvo, Mayer / Yu, Philip L. H. Publisher: Springer ISBN: 9783030068042 Cover: PAPERBACK Date: 2018年12月 DESCRIPTION This book demonstrates that nonparametric statistics can be taught from a parametric point of view. As a result, one can exploit various parametric tools such as the use of the likelihood function, penalized likelihood and score functions to not only derive well-known tests but to also go beyond and make use of Bayesian methods to analyze ranking data. The book bridges the gap between parametric and nonparametric statistics and presents the best practices of the former while enjoying the robustness properties of the latter. This book can be used in a graduate course in nonparametrics, with parts being accessible to senior undergraduates. In addition, the book will be of wide interest to statisticians and researchers in applied fields. Table of Contents I. Introduction and Fundamentals.- Introduction.- Fundamental Concepts in Parametric Inference.- II. Modern Nonparametric Statistical Methods.- Smooth Goodness of Fit Tests.- One-Sample and Two-Sample Problems.- Multi-Sample Problems.- Tests for Trend and Association.- Optimal Rank Tests.- Efficiency.- III. Selected Applications.- Multiple Change-Point Problems.- Bayesian Models for Ranking Data.- Analysis of Censored Data.- A. Description of Data Sets. TABLE OF CONTENTS This book demonstrates that nonparametric statistics can be taught from a parametric point of view. As a result, one can exploit various parametric tools such as the use of the likelihood function, penalized likelihood and score functions to not only derive well-known tests but to also go beyond and make use of Bayesian methods to analyze ranking data. The book bridges the gap between parametric and nonparametric statistics and presents the best practices of the former while enjoying the robustness properties of the latter. This book can be used in a graduate course in nonparametrics, with parts being accessible to senior undergraduates. In addition, the book will be of wide interest to statisticians and researchers in applied fields.
|