Lumley Complex Surveys

A Guide to Analysis Using R
1. Auflage 2010
ISBN: 978-0-470-58005-9
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 296 Seiten, E-Book

Reihe: Wiley Series in Survey Methodology

A complete guide to carrying out complex survey analysis usingR
As survey analysis continues to serve as a core component ofsociological research, researchers are increasingly relying upondata gathered from complex surveys to carry out traditionalanalyses. Complex Surveys is a practical guide to theanalysis of this kind of data using R, the freely available anddownloadable statistical programming language. As creator of thespecific survey package for R, the author provides the ultimatepresentation of how to successfully use the software for analyzingdata from complex surveys while also utilizing the most currentdata from health and social sciences studies to demonstrate theapplication of survey research methods in these fields.
The book begins with coverage of basic tools and topics withinsurvey analysis such as simple and stratified sampling, clustersampling, linear regression, and categorical data regression.Subsequent chapters delve into more technical aspects of complexsurvey analysis, including post-stratification, two-phase sampling,missing data, and causal inference. Throughout the book, anemphasis is placed on graphics, regression modeling, and two-phasedesigns. In addition, the author supplies a unique discussion ofepidemiological two-phase designs as well as probability-weightingfor causal inference. All of the book's examples and figures aregenerated using R, and a related Web site provides the R code thatallows readers to reproduce the presented content. Each chapterconcludes with exercises that vary in level of complexity, anddetailed appendices outline additional mathematical andcomputational descriptions to assist readers with comparing resultsfrom various software systems.
Complex Surveys is an excellent book for courses onsampling and complex surveys at the upper-undergraduate andgraduate levels. It is also a practical reference guide for appliedstatisticians and practitioners in the social and health scienceswho use statistics in their everyday work.

Autoren/Hrsg.

Lumley, Thomas S.

Inhaltsverzeichnis

Acknowledgments.
Preface.
Acronyms.
1 Basic Tools.
1.1 Goals of inference.
1.2 An introduction to the data.
1.3 Obtaining the software.
1.4 Using R.
Exercises.
2 Simple and Stratified sampling.
2.1 Analysing simple random samples.
2.2 Stratified sampling.
2.3 Replicate weights.
2.4 Other population summaries.
2.5 Estimates in subpopulations.
2.6 Design of stratified samples.
Exercises.
3 Cluster sampling.
3.1 Introduction.
3.2 Describing multistage designs to R.
3.3 Sampling by size.
3.4 Repeated measurements.
Exercises.
4 Graphics.
4.1 Why is survey data different?
4.2 Plotting a table.
4.3 One continuous variable.
4.4 Two continuous variables.
4.5 Conditioning plots.
4.6 Maps.
Exercises.
5 Ratios and linear regression.
5.1 Ratio estimation.
5.2 Linear regression.
5.3 Is weighting needed in regression models?
6 Categorical data regression 109.
6.1 Logistic regression 110.
6.2 Ordinal regression 117.
6.3 Loglinear models 123.
7 Poststratification, raking and calibration.
7.1 Introduction.
7.2 Poststratification.
7.3 Raking.
7.4 Generalized raking, GREG estimation, and calibration.
7.5 Basu's elephants.
7.6 Selecting auxiliary variables for nonresponse.
Exercises.
8 Twophase sampling.
8.1 Multistage and multiphase sampling.
8.2 Sampling for stratification.
8.3 The case-control design.
8.4 Sampling from existing cohorts.
8.5 Using auxiliary information from phase one.
Exercises.
9 Missing data.
9.1 Item nonresponse.
9.2 Twophase estimation for missing data.
9.3 Imputation of missing data.
Exercises.
10 Causal inference.
10.1 IPTW estimators.
10.2 Marginal Structural Models.
Appendix A: Analytic details.
A.1 Asymptotics.
A.2 Variances by linearization.
A.3 Tests in contingency tables.
A.4 Multiple imputation.
A.5 Calibration and influence functions.
A.6 Calibration in randomized trials and ANCOVA.
Appendix B: Basic R.
B.1 Reading data.
B.2 Data manipulation.
B.3 Randomness.
B.4 Methods and objects.
B.5 Writing functions.
Appendix C: Computational details.
C.1 Linearization.
C.2 Replicate weights.
C.3 Scatterplot smoothers.
C.4 Quantiles.
C.5 Bug reports and feature requests.
Appendix D: Databasebacked design objects.
D.1 Large data.
D.2 Setting up database interfaces.
Appendix E: Extending the survey package.
E.1 A case study: negative binomial regression.
E.2 Using a Poisson model.
E.3 Replicate weights.
E.4 Linearization.
References.
Author Index.
Topic Index.

Über Autor(innen)

THOMAS LUMLEY, PHD, is Associate Professor of Biostatistics at the University of Washington. He has published numerous journal articles in his areas of research interest, which include regression modeling, clinical trials, statistical computing, and survey research. Dr. Lumley created the survey package that currently accompanies the R software package, and he is also coauthor of Biostatistics: A Methodology for the Health Sciences, Second Edition, published by Wiley.