Muutke küpsiste eelistusi

Maximum Likelihood Estimation for Sample Surveys [Kõva köide]

(University of Wollongong, New South Wales, Australia), (Texas A&M University, College Station, USA), (University of Wollongong, New South Wales, Australia), (The Australian National University, Canberra , Australia)
Teised raamatud teemal:
Maximum Likelihood Estimation for Sample SurveysSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781584886327.html
Märksõnad:
Chambers (U. of Wollongong, Australia), David G. Steel, Suojin Wang (Texas A&M U.), and Alan Welsh (Australian National U.-Canberra) explain to statisticians how to set up and conduct maximum likelihood analysis with sample survey data. They discuss alternative likelihood-based methods for sample survey data, populations with independent units, regression models, clustered populations, informative nonresponse, and maximum likelihood in other complicated situations. Annotation ©2012 Book News, Inc., Portland, OR (booknews.com)

Sample surveys provide data used by researchers in a large range of disciplines to analyze important relationships using well-established and widely used likelihood methods. The methods used to select samples often result in the sample differing in important ways from the target population and standard application of likelihood methods can lead to biased and inefficient estimates.

Maximum Likelihood Estimation for Sample Surveys presents an overview of likelihood methods for the analysis of sample survey data that account for the selection methods used, and includes all necessary background material on likelihood inference. It covers a range of data types, including multilevel data, and is illustrated by many worked examples using tractable and widely used models. It also discusses more advanced topics, such as combining data, non-response, and informative sampling.

The book presents and develops a likelihood approach for fitting models to sample survey data. It explores and explains how the approach works in tractable though widely used models for which we can make considerable analytic progress. For less tractable models numerical methods are ultimately needed to compute the score and information functions and to compute the maximum likelihood estimates of the model parameters. For these models, the book shows what has to be done conceptually to develop analyses to the point that numerical methods can be applied.

Designed for statisticians who are interested in the general theory of statistics, Maximum Likelihood Estimation for Sample Surveys is also aimed at statisticians focused on fitting models to sample survey data, as well as researchers who study relationships among variables and whose sources of data include surveys.

Arvustused

"This book makes a strong contribution to the model-based approach. This book is the first thorough, self-contained development of the likelihood theory on sample survey data. The authors demonstrate application of their maximum likelihood method in many important estimation problems. the maximum likelihood approach presented in this book allows for further scientific discoveries and further new results when dealing with complex statistical data." Imbi Traat, International Statistical Review (2013), 81, 2

"The authors masterfully accomplish their goal and present us with an excellent and well-written book on model-based analysis for sample surveys. For the models with a mathematically tractable likelihood function, the authors develop the theory to the point ready for numerical implementation; for the mathematical intractable case, they also establish a conceptual procedure that allows future numerical research and implementation. the book has something for just about every applied statistician and practitioner whose work is related to sampling survey design and analysis. elegant presentation of the theory and clarity of writing make it easy to read. a valuable theoretical contribution to the area of survey sampling and provides a thoughtful basis for further applied research. I also recommend this book as a key reference for graduate students in applied statistics and related areas." Cheng Peng, Mathematical Reviews, May 2013

"This sinewy and satisfying book presents a thorough development of the use of likelihood techniques for the analysis of sample survey data, that is, for model-based analysis. the authors have taken care to lace the presentation with generous explanations, drawing connections between the content and familiar examples in thoughtful ways, and occasionally providing guidance from their own experience. I particularly enjoyed the use of a stratified population to explain the difference between aggregated and disaggregated estimation. Here, and in similar places, the book shines. well organized [ and] extremely well edited " Andrew Robinson, Australian & New Zealand Journal of Statistics, 2013

Preface xv
1 Introduction
1(24)
1.1 Nature and role of sample surveys
1(2)
1.2 Sample designs
3(3)
1.3 Survey data, estimation and analysis
6(2)
1.4 Why analysts of survey data should be interested in maximum likelihood estimation
8(1)
1.5 Why statisticians should be interested in the analysis of survey data
9(1)
1.6 A sample survey example
9(3)
1.7 Maximum likelihood estimation for infinite populations
12(9)
1.7.1 Data
12(1)
1.7.2 Statistical models
13(1)
1.7.3 Likelihood
14(1)
1.7.4 Score and information functions
15(2)
1.7.5 Maximum likelihood estimation
17(2)
1.7.6 Hypothesis tests
19(1)
1.7.7 Confidence intervals
20(1)
1.7.8 Sufficient and ancillary statistics
20(1)
1.8 Bibliographic notes
21(4)
2 Maximum likelihood theory for sample surveys
25(30)
2.1 Introduction
25(1)
2.2 Maximum likelihood using survey data
26(7)
2.2.1 Basic concepts
26(4)
2.2.2 The missing information principle
30(3)
2.3 Illustrative examples with complete response
33(6)
2.3.1 Estimation of a Gaussian mean: Noninformative selection
33(4)
2.3.2 Estimation of an exponential mean: Cutoff sampling
37(1)
2.3.3 Estimation of an exponential mean: Size-biased sampling
38(1)
2.4 Dealing with nonresponse
39(3)
2.4.1 The score and information functions under nonresponse
40(1)
2.4.2 Noninformative nonresponse
41(1)
2.5 Illustrative examples with nonresponse
42(9)
2.5.1 Estimation of a Gaussian mean under noninformative nonresponse: Noninformative selection
42(1)
2.5.2 Estimation of a Gaussian mean under noninformative item nonresponse: Noninformative selection
43(4)
2.5.3 Estimation of a Gaussian mean under informative unit nonresponse: Noninformative selection
47(2)
2.5.4 Estimation of an exponential mean under informative nonresponse: Cutoff sampling
49(2)
2.6 Bibliographic notes
51(4)
3 Alternative likelihood-based methods for sample survey data
55(34)
3.1 Introduction
55(5)
3.1.1 Design-based analysis for population totals
56(4)
3.2 Pseudo-likelihood
60(4)
3.2.1 Maximum pseudo-likelihood estimation
60(2)
3.2.2 Pseudo-likelihood for an exponential mean under size-biased sampling
62(1)
3.2.3 Pseudo-Likelihood for an exponential mean under cutoff sampling
63(1)
3.3 Sample likelihood
64(8)
3.3.1 Maximum sample likelihood for an exponential mean under size-biased sampling
66(4)
3.3.2 Maximum sample likelihood for an exponential mean under cutoff sampling
70(2)
3.4 Analytic comparisons of maximum likelihood, pseudo-likelihood and sample likelihood estimation
72(3)
3.5 The role of sample inclusion probabilities in analytic analysis
75(8)
3.6 Bayesian analysis
83(2)
3.7 Bibliographic notes
85(4)
4 Populations with independent units
89(56)
4.1 Introduction
89(1)
4.2 The score and information functions for independent units
89(2)
4.3 Bivariate Gaussian populations
91(5)
4.4 Multivariate Gaussian populations
96(8)
4.5 Non-Gaussian auxiliary variables
104(18)
4.5.1 Modeling the conditional distribution of the survey variable
109(2)
4.5.2 Modeling the marginal distribution of the auxiliary variable
111(4)
4.5.3 Maximum likelihood analysis for μ and σ2
115(2)
4.5.4 Fitting the auxiliary variable distribution via method of moments
117(4)
4.5.5 Semiparametric estimation
121(1)
4.6 Stratified populations
122(4)
4.7 Multinomial populations
126(9)
4.8 Heterogeneous multinomial logistic populations
135(9)
4.9 Bibliographic notes
144(1)
5 Regression models
145(28)
5.1 Introduction
145(3)
5.2 A Gaussian example
148(4)
5.3 Parameterization in the Gaussian model
152(2)
5.4 Other methods of estimation
154(3)
5.5 Non-Gaussian models
157(1)
5.6 Different auxiliary variable distributions
158(6)
5.6.1 The folded Gaussian model for the auxiliary variable
159(1)
5.6.2 Regression in stratified populations
160(4)
5.7 Generalized linear models
164(4)
5.7.1 Binary regression
165(1)
5.7.2 Generalized linear regression
166(2)
5.8 Semiparametric and nonparametric methods
168(2)
5.9 Bibliographic notes
170(3)
6 Clustered populations
173(44)
6.1 Introduction
173(5)
6.2 A Gaussian group dependent model
178(15)
6.2.1 Auxiliary information at the unit level
178(9)
6.2.2 Auxiliary information at the cluster level
187(4)
6.2.3 No auxiliary information
191(2)
6.3 A Gaussian group dependent regression model
193(8)
6.4 Extending the Gaussian group dependent regression model
201(2)
6.5 Binary group dependent models
203(4)
6.6 Grouping models
207(7)
6.7 Bibliographic notes
214(3)
7 Informative nonresponse
217(82)
7.1 Introduction
217(6)
7.2 Nonresponse in innovation surveys
223(19)
7.2.1 The mixture approach
224(4)
7.2.2 The mixture approach with an additional variable
228(5)
7.2.3 The mixture approach with a follow up survey
233(4)
7.2.4 The selection approach
237(5)
7.3 Regression with item nonresponse
242(25)
7.3.1 Item nonresponse in y
248(2)
7.3.2 Item nonresponse in x
250(4)
7.3.3 Selection models for item nonresponse in y
254(13)
7.4 Regression with arbitrary nonresponse
267(23)
7.4.1 Calculations for s01
280(1)
7.4.2 Calculations for s10
281(3)
7.4.3 Calculations for s00
284(6)
7.5 Imputation versus estimation
290(5)
7.6 Bibliographic notes
295(4)
8 Maximum likelihood in other complicated situations
299(54)
8.1 Introduction
299(2)
8.2 Likelihood analysis under informative selection
301(15)
8.2.1 When is selection informative?
301(1)
8.2.2 Maximum likelihood under informative Hartley-Rao sampling
302(4)
8.2.3 Maximum sample likelihood under informative Hartley-Rao sampling
306(3)
8.2.4 An extension to the case with auxiliary variables
309(1)
8.2.5 Informative stratification
310(6)
8.3 Secondary analysis of sample survey data
316(5)
8.3.1 Data structure in secondary analysis
316(1)
8.3.2 Approximate maximum likelihood with partial information
317(4)
8.4 Combining summary population information with likelihood analysis
321(20)
8.4.1 Summary population information
321(2)
8.4.2 Linear regression with summary population information
323(6)
8.4.3 Logistic regression with summary population information
329(4)
8.4.4 Smearing and saddlepoint approximations under case-control sampling
333(3)
8.4.5 Variance estimation
336(3)
8.4.6 A derivation of the saddlepoint approximation in Subsection 8.4.3
339(2)
8.5 Likelihood analysis with probabilistically linked data
341(9)
8.5.1 A model for probabilistic linkage
342(2)
8.5.2 Linear regression with population-linked data
344(4)
8.5.3 Linear regression with sample-linked data
348(2)
8.6 Bibliographic notes
350(3)
Notation 353(4)
Author Index 357(4)
Example Index 361(4)
Subject Index 365
Raymond L. Chambers, David G. Steel, Suojin Wang, Alan Welsh