Atnaujinkite slapukų nuostatas

Statistical Analysis with Measurement Error or Misclassification: Strategy, Method and Application 1st ed. 2017 [Kietas viršelis]

  • Formatas: Hardback, 479 pages, aukštis x plotis: 235x155 mm, weight: 1149 g, 1 Illustrations, color; 15 Illustrations, black and white; XXVII, 479 p. 16 illus., 1 illus. in color., 1 Hardback
  • Serija: Springer Series in Statistics
  • Išleidimo metai: 03-Aug-2017
  • Leidėjas: Springer-Verlag New York Inc.
  • ISBN-10: 1493966383
  • ISBN-13: 9781493966387
Kitos knygos pagal šią temą:
Statistical Analysis with Measurement Error or Misclassification: Strategy, Method and Application 1st ed. 2017Didesnis paveikslėlis
  • Formatas: Hardback, 479 pages, aukštis x plotis: 235x155 mm, weight: 1149 g, 1 Illustrations, color; 15 Illustrations, black and white; XXVII, 479 p. 16 illus., 1 illus. in color., 1 Hardback
  • Serija: Springer Series in Statistics
  • Išleidimo metai: 03-Aug-2017
  • Leidėjas: Springer-Verlag New York Inc.
  • ISBN-10: 1493966383
  • ISBN-13: 9781493966387
Kitos knygos pagal šią temą:
Pastovi nuoroda: https://www.kriso.lt/db/9781493966387.html
Raktažodžiai:
This monograph on measurement error and misclassification covers a broad range of problems and emphasizes unique features in modeling and analyzing problems arising from medical research and epidemiological studies. Many measurement error and misclassification problems have been addressed in various fields over the years as well as with a wide spectrum of data, including event history data (such as survival data and recurrent event data), correlated data (such as longitudinal data and clustered data), multi-state event data, and data arising from case-control studies. Statistical Analysis with Measurement Error or Misclassification:  Strategy, Method and Application brings together assorted methods in a single text and provides an update of recent developments for a variety of settings. Measurement error effects and strategies of handling mismeasurement for different models are closely examined in combination with applications to specific problems. Readers with diverse backgrounds and objectives can utilize this text. Familiarity with inference methodssuch as likelihood and estimating function theoryor modeling schemes in varying settingssuch as survival analysis and longitudinal data analysiscan result in a full appreciation of the material, but it is not essential since each chapter provides basic inference frameworks and background information on an individual topic to ease the access of the material.  The text is presented in a coherent and self-contained manner and highlights the essence of commonly used modeling and inference methods. This text can serve as a reference book for researchers  interested in statistical methodology for handling data with measurement error or misclassification; as a textbook for graduate students, especially for those majoring in statistics and biostatistics; or as a book for applied statisticians whose interest focuses on analysis of error-contaminated data. Grace Y. Yi is Professor of Statistics and University Research Chair at the University of Waterloo. She is the 2010 winner of the CRM-SSC Prize, an honor awarded in recognition of a statistical scientist's professional accomplishments in research during the first 15 years after having received a doctorate. She is a Fellow of the American Statistical Association and an Elected Member of the International Statistical Institute. 

Recenzijos

This book constitutes a comprehensive and thorough treatment of measurement error and misclassification in survival data, recurrent event data, longitudinal data, multi-state models, and case-control studies. the book is well written and a pleasure to read. (Rianne Jacobs, ISCB News, iscb.info, Issue 65, June, 2018)

This book successfully collects, compiles, organizes, and presents the literature on the newly developed and earlier existing topics of measurement error models and misclassification in a crisp and concise way without losing the clarity in understanding. I am sure it will stimulate researchers in and newcomers to this area. (Shalabh, Mathematical Reviews, June, 2018) This book covers a wide range of topics in a unified framework where measurement error and misclassification problems receive careful treatments, from both practical and theoretical points of view. This book can serve well as a textbook for a graduate-level course on measurement error in a (bio)statistics department . Besides ample real life applications presented in the book, from which students can appreciate practical relevance of measurement error problems . (Xianzheng Huang, Journal of the American Statistical Association JASA, Vol. 113 (522), 2018)

1 Inference Framework and Method
1(42)
1.1 Framework and Objective
1(2)
1.2 Modeling and Estimator
3(7)
1.2.1 Parameter and Identifiability
3(1)
1.2.2 Parameter Estimator
4(3)
1.2.3 Concepts in Asymptotic Sense
7(3)
1.3 Estimation Methods
10(17)
1.3.1 Likelihood Method
10(4)
1.3.2 Estimating Equations
14(3)
1.3.3 Generalized Method of Moments
17(4)
1.3.4 Profiling Method
21(6)
1.4 Model Misspecification
27(4)
1.5 Covariates and Regression Models
31(1)
1.6 Bibliographic Notes and Discussion
32(1)
1.7 Supplementary Problems
33(10)
2 Measurement Error and Misclassification: Introduction
43(44)
2.1 Measurement Error and Misclassification
43(2)
2.2 An Illustration of Measurement Error Effects
45(4)
2.3 The Scope of Analysis with Mismeasured Data
49(1)
2.4 Issues in the Presence of Measurement Error
50(4)
2.5 General Strategy of Handling Measurement Error
54(18)
2.5.1 Likelihood-Based Correction Methods
55(3)
2.5.2 Unbiased Estimating Functions Methods
58(4)
2.5.3 Methods of Correcting Naive Estimators
62(3)
2.5.4 Discussion
65(7)
2.7 Measurement Error and Misclassification Examples
72(5)
2.7.1 Survival Data Example: Busselton Health Study
72(1)
2.7.2 Recurrent Event Example: rhDNase Data
73(1)
2.7.3 Longitudinal Data Example: Framingham Heart Study
74(1)
2.7.4 Multi-State Model Example: HL Data
75(1)
2.7.5 Case-Control Study Example: HSV Data
75(2)
2.8 Bibliographic Notes and Discussion
77(2)
2.9 Supplementary Problems
79(8)
3 Survival Data with Measurement Error
87(64)
3.1 Framework of Survival Analysis: Models and Methods
88(12)
3.1.1 Basic Measures
88(1)
3.1.2 Some Parametric Modeling Strategies
89(2)
3.1.3 Regression Models
91(3)
3.1.4 Special Features of Survival Data
94(2)
3.1.5 Likelihood Method
96(1)
3.1.6 Model-Dependent Inference Methods
97(3)
3.2 Measurement Error Effects and Inference Framework
100(5)
3.2.1 Induced Hazard Function
100(2)
3.2.2 Discussion and Assumptions
102(3)
3.3 Approximate Methods for Measurement Error Correction
105(2)
3.3.1 Regression Calibration Method
105(2)
3.3.2 Simulation Extrapolation Method
107(1)
3.4 Methods Based on the Induced Hazard Function
107(5)
3.4.1 Induced Likelihood Method
108(1)
3.4.2 Induced Partial Likelihood Method
109(3)
3.5 Likelihood-Based Methods
112(6)
3.5.1 Insertion Correction: Piecewise-Constant Method
112(4)
3.5.2 Expectation Correction: Two-Stage Method
116(2)
3.6 Methods Based on Estimating Functions
118(12)
3.6.1 Proportional Hazards Model
119(3)
3.6.2 Simulation Study
122(1)
3.6.3 Additive Hazards Model
123(6)
3.6.4 An Example: Analysis of ACTG175 Data
129(1)
3.7 Misclassification of Discrete Covariates
130(6)
3.7.1 Methods with Known Misclassification Probabilities
132(2)
3.7.2 Method with a Validation Sample
134(1)
3.7.3 Method with Replicates
135(1)
3.8 Multivariate Survival Data with Covariate Measurement Error
136(8)
3.8.1 Marginal Approach
137(1)
3.8.2 Dependence Parameter Estimation of Copula Models
138(2)
3.8.3 EM Algorithm with Frailty Measurement Error Model
140(4)
3.9 Bibliographic Notes and Discussion
144(2)
3.10 Supplementary Problems
146(5)
4 Recurrent Event Data with Measurement Error
151(42)
4.1 Analysis Framework for Recurrent Events
151(12)
4.1.1 Notation and Framework
152(3)
4.1.2 Poisson Process and Renewal Process
155(2)
4.1.3 Covariates and Extensions
157(6)
4.2 Measurement Error Effects on Poisson Process
163(3)
4.3 Directly Correcting Naive Estimators When Assessment Times are Discrete
166(4)
4.4 Counting Processes with Observed Event Times
170(3)
4.5 Poisson Models for Interval Counts
173(3)
4.6 Marginal Methods for Interval Count Data with Measurement Error
176(4)
4.7 An Example: rhDNase Data
180(1)
4.8 Bibliographic Notes and Discussion
181(1)
4.9 Supplementary Problems
182(11)
5 Longitudinal Data with Covariate Measurement Error
193(64)
5.1 Error-Free Inference Frameworks
193(9)
5.1.1 Estimating Functions Based on Mean Structure
195(3)
5.1.2 Generalized Linear Mixed Models
198(2)
5.1.3 Nonlinear Mixed Models
200(2)
5.2 Measurement Error Effects
202(7)
5.2.1 Marginal Analysis Based on GEE with Independence Working Matrix
202(3)
5.2.2 Mixed Effects Models
205(4)
5.3 Estimating Function Methods
209(6)
5.3.1 Expected Estimating Equations
211(2)
5.3.2 Corrected Estimating Functions
213(2)
5.4 Likelihood-Based Inference
215(5)
5.4.1 Observed Likelihood
216(1)
5.4.2 Three-Stage Estimation Method
217(1)
5.4.3 EM Algorithm
218(2)
5.4.4 Remarks
220(1)
5.5 Inference Methods in the Presence of Both Measurement Error and Missingness
220(18)
5.5.1 Missing Data and Inference Methods
221(3)
5.5.2 Strategy of Correcting Measurement Error and Missingness Effects
224(2)
5.5.3 Sequential Corrections
226(5)
5.5.4 Simultaneous Inference to Accommodating Missingness and Measurement Error Effects
231(3)
5.5.5 Discussion
234(1)
5.5.6 Simulation and Example
235(3)
5.6 Joint Modeling of Longitudinal and Survival Data with Measurement Error
238(8)
5.6.1 Likelihood-Based Methods
239(3)
5.6.2 Conditional Score Method
242(4)
5.7 Bibliographic Notes and Discussion
246(1)
5.8 Supplementary Problems
247(10)
6 Multi-State Models with Error-Prone Data
257(44)
6.1 Framework of Multi-State Models
258(13)
6.1.1 Notation and Setup
258(3)
6.1.2 Continuous-Time Homogeneous Markov Processes
261(2)
6.1.3 Continuous-Time Nonhomogeneous Markov Processes
263(1)
6.1.4 Discrete-Time Markov Models
264(1)
6.1.5 Regression Models
265(1)
6.1.6 Likelihood Inference
266(2)
6.1.7 Transition Models
268(3)
6.2 Two-State Markov Models with Misclassified States
271(4)
6.3 Multi-State Models with Misclassified States
275(6)
6.4 Markov Models with States Denned by Discretizing an Error-Prone Variable
281(5)
6.5 Transition Models with Covariate Measurement Error
286(4)
6.6 Transition Models with Measurement Error in Response and Covariates
290(4)
6.7 Bibliographic Notes and Discussion
294(1)
6.8 Supplementary Problems
295(6)
7 Case-Control Studies with Measurement Error or Misclassification
301(52)
7.1 Introduction of Case-Control Studies
302(13)
7.1.1 Basic Concepts
302(1)
7.1.2 Unstratified Studies
302(2)
7.1.3 Matching and Stratification
304(3)
7.1.4 Regression Model
307(1)
7.1.5 Retrospective Sampling and Inference Strategy
308(2)
7.1.6 Analysis of Case-Control Data with Prospective Logistic Model
310(5)
7.2 Measurement Error Effects
315(3)
7.3 Interacting Covariates Subject to Misclassification
318(7)
7.4 Retrospective Pseudo-Likelihood Method for Unmatched Designs
325(6)
7.5 Correction Method for Matched Designs
331(5)
7.6 Two-Phase Design with Misclassified Exposure Variable
336(3)
7.7 Bibliographic Notes and Discussion
339(2)
7.8 Supplementary Problems
341(12)
8 Analysis with Mismeasured Responses
353(42)
8.1 Introduction
353(2)
8.2 Effects of Misclassified Responses on Model Structures
355(8)
8.2.1 Univariate Binary Response with Misclassification
356(2)
8.2.2 Univariate Binary Data with Misclassification in Response and Measurement Error in Covariates
358(2)
8.2.3 Clustered Binary Data with Error in Responses
360(3)
8.3 Methods for Univariate Error-Prone Response
363(5)
8.4 Logistic Regression Model with Measurement Error in Response and Covariates
368(4)
8.5 Least Squares Methods with Measurement Error in Response and Covariates
372(4)
8.6 Correlated Binary Data with Diagnostic Error
376(2)
8.7 Marginal Method for Clustered Binary Data with Misclassification in Responses
378(7)
8.7.1 Models and Method
378(6)
8.7.2 An Example: CCHS Data
384(1)
8.8 Bibliographic Notes and Discussion
385(1)
8.9 Supplementary Problems
386(9)
9 Miscellaneous Topics
395(16)
9.1 General Issues on Measurement Error Models
396(11)
9.2 Causal Inference with Measurement Error
407(1)
9.3 Statistical Software on Measurement Error and Misclassification Models
408(3)
Appendix
411(10)
A Matrix Algebra: Some Notation and Facts
411(10)
A.2 Definitions and Facts
413(2)
A.3 Newton-Raphson and Fisher-Scoring Algorithms
415(2)
A.4 The Bootstrap and Jackknife Methods
417(2)
A.5 Monte Carlo Method and MCEM Algorithm
419(2)
References 421(42)
Author Index 463(8)
Subject Index 471
Grace Y. Yi is Professor of Statistics and University Research Chair at the University of Waterloo. Her broad research interests include measurement error models, missing data problems, high dimensional data analysis, survival data and longitudinal data analysis, estimating function and likelihood methods, and medical applications. Prof. Yi received her Ph.D. in Statistics from the University of Toronto in 2000.  She is the 2010 winner of the CRM-SSC Prize, an honor awarded in recognition of a statistical scientist's professional accomplishments in research during the first 15 years after having received a doctorate. She was a recipient of the prestigious University Faculty Award granted by the Natural Sciences and Engineering Research Council of Canada (NSERC). She serves as an associate editor for several statistical journals, and is the editor of the Canadian Journal of Statistics (2016-2018). She is a Fellow of the American Statistical Association, andan Elected Member of the International Statistical Institute. She is President of the Biostatistics Section of the Statistical Society of Canada in 2016, and the Founder and Chair of the first chapter (Canada Chapter) of the  International Chinese Statistical Association.