Achim Dörre, Takeshi Emura

Analysis of Doubly Truncated Data

An Introduction

• Broschiertes Buch

Produktbeschreibung

This book introduces readers to statistical methodologies used to analyze doubly truncated data. The first book exclusively dedicated to the topic, it provides likelihood-based methods, Bayesian methods, non-parametric methods, and linear regression methods. These procedures can be used to effectively analyze continuous data, especially survival data arising in biostatistics and economics. Because truncation is a phenomenon that is often encountered in non-experimental studies, the methods presented here can be applied to many branches of science. The book provides R codes for most of the statistical methods, to help readers analyze their data. Given its scope, the book is ideally suited as a textbook for students of statistics, mathematics, econometrics, and other fields.

Produktdetails

• SpringerBriefs in Statistics
• Verlag: Springer / Springer Nature Singapore / Springer, Berlin
• Artikelnr. des Verlages: 978-981-13-6240-8
• 1st ed. 2019
• Seitenzahl: 128
• Erscheinungstermin: 22. Mai 2019
• Englisch
• Abmessung: 235mm x 155mm x 8mm
• Gewicht: 212g
• ISBN-13: 9789811362408
• ISBN-10: 9811362408
• Artikelnr.: 54799761

Autorenporträt

Achim Dörre, University of Rostock Takeshi Emura, Chang Gung University

Inhaltsangabe

Chapter 1: Introduction to double-truncation.- Chapter 2: Parametric inference under special exponential family.- Chapter 3: Parametric inference under location-scale family.- Chapter 4: Bayes inference.- Chapter 5: Nonparametric inference.- Chapter 6: Linear regression.- Appendix A: Data (if German company data are available).- Appendix B: R codes for inference under exponential family.- Appendix C: R codes for inference under location-scale family.- Appendix D: R codes for Bayes inference.- Appendix E: R codes for linear regression.

Rezensionen

"The aim of this book is to provide some fundamental ideas and methodologies for analysing doubly truncated data. ... The methodology of this book could be helpful to avoid a systematic bias in the contents of data due to loss of information." (Nikita E. Ratanov, zbMATH 1434.62008, 2020)