Practical Tools for Designing and Weighting Survey Samples
-10%
portes grátis
Practical Tools for Designing and Weighting Survey Samples
Dever, Jill A.; Kreuter, Frauke; Valliant, Richard
Springer International Publishing AG
11/2018
468
Dura
Inglês
9783319936314
Pré-lançamento - envio 15 a 20 dias após a sua edição
This book explains approaches long used by survey statisticians, illustrating how existing software can be used to solve survey problems, and developing some specialized software where needed.
PrefaceAcknowledgements 1 An Overview of Sample Design and Weighting1.1 Background and Terminology1.2 Chapter Guide Part I Designing Single-Stage Sample Surveys2 Project 1: Design a Single-Stage Personnel Survey2.1 Specifications for the Study2.2 Questions Posed by the Design Team2.3 Preliminary Analyses2.4 Documentation2.5 Next Steps 3 Sample Design and Sample Size for Single-Stage Surveys 3.1 Determining a Sample Size for a Single-Stage Design 3.1.1 Simple Random Sampling3.1.2 Stratified Simple Random Sampling3.2 Finding Sample Sizes When Sampling with Varying Probabilities 3.2.1 Probability Proportional to Size Sampling3.2.2 Regression Estimates of Totals3.3 Other Methods of Sampling3.4 Estimating Population Parameters from a Sample3.5 Special Topics3.5.1 Rare Characteristics3.5.2 Domain Estimates3.6 More Discussion of Design Effects3.7 Software for Sample Selection3.7.1 R Packages3.7.2 SAS PROC SURVEYSELECTExercises 4 Power Calculations and Sample Size Determination 4.1 Terminology and One-Sample Tests4.2 Power in a One-Sample Test4.3 Two-Sample Tests4.3.1 Differences in Means4.3.2 Differences in Proportions4.3.3 Special Case: Relative Risk4.3.4 Special Case: Effect Sizes4.4 R Power Functions4.5 Power and Sample Size Calculations in SAS. Exercises 5 Mathematical Programming5.1 Multicriteria Optimization5.2 Microsoft Excel Solver5.3 SAS PROC NLP5.4 SAS PROC OPTMODEL5.5 R Alabama Package <6 Outcome Rates and Effect on Sample Size6.1 Disposition Codes6.2 Definitions of Outcome Rates6.3 Sample Units with Unknown AAPOR Classification6.4 Weighted Versus Unweighted Rates6.5 Accounting for Sample Losses in Determining Initial Sample Size6.5.1 Sample Size Inflation Rates at Work6.5.2 ReplicatesExercises 7 The Personnel Survey Design Project: One Solution 7.1 Overview of the Project 7.2 Formulate the Optimization Problem7.2.1 Objective Function 7.2.2 Decision Variables 7.2.3 Optimization Parameters7.2.4 Specified Survey Constraints 7.3 One Solution 7.3.1 Power Analyses7.3.2 Optimization Results7.4 Additional Sensitivity Analysis7.5 Conclusion Part II Multistage Designs 8 Project 2: Designing an Area Sample 9 Designing Multistage Samples 9.1 Types of PSUs 9.2 Basic Variance Results 9.2.1 Two-Stage Sampling 9.2.2 Nonlinear Estimators in Two-Stage Sampling 9.2.3 More General Two-Stage Designs 9.2.4 Three-Stage Sampling 9.3 Cost Functions and Optimal Allocations for Multistage Sampling 9.3.1 Two-Stage Sampling When Numbers of Sample PSUs and Elements per PSU Are Adjustable 9.3.2 Three-Stage Sampling When Sample Sizes Are Adjustable 9.3.3 Two- and Three-Stage Sampling with a Fixed Set of PSUs 9.4 Estimating Measures of Homogeneity and Variance Components9.4.1 Two-Stage Sampling 9.4.2 Three-Stage Sampling 9.4.3 Using Anticipated Variances The lme4 R package has been updated so that the syntax in the 1st edition no longer works. We will revise the examples in this section for the new version of the package.9.5 Stratification of PSUs 9.6 Identifying Certainties Exercises 10 Area Sampling10.1 Census Geographic Units10.2 Census Data and American Community Survey Data10.3 Units at Different Stages of Sampling10.3.1 Primary Sampling Units10.3.2 Secondary Sampling Units10.3.3 Ultimate Sampling Units10.4 Examples of Area Probability Samples10.4.1 Current Population Survey10.4.2 National Survey on Drug Use and Health10.4.3 Panel Arbeitsmarkt und Soziale Sicherung10.5 Composite MOS for Areas10.5.1 Designing the Sample from Scratch10.5.2 Using the Composite MOS with an Existing PSU Sample10.6 Effects of Population Change: The New Construction Issue10.7 Special Address Lists10.7.1 Allocations in ABS using Mathematical Programming Mathematical programming allows efficient allocations to be made to domains (e.g., age groups) using information on housing units that can be purchased from commercial list makers. Discussion and examples will be added to illustrate this technique. The following article will be the basis for examples: Valliant, R., Hubbard, F., Lee, S., Chang, W. (2014). "Efficient Use of Commercial Lists in Household Sampling", Journal of Survey Statistics and Methodology, 2, 182-209.Exercises 11 The Area Sample Design: One Solution Part III Survey Weights and Analyses12 Project 3: Weighting a Personnel Survey 13 Basic Steps in Weighting13.1 Overview of Weighting13.2 Theory of Weighting and Estimation13.3 Base Weights13.4 Adjustments for Unknown Eligibility13.5 Adjustments for Nonresponse13.5.1 Weighting Class Adjustments13.5.2 Propensity Score Adjustments13.5.3 Classification Algorithms13.6 Collapsing Predefined Classes13.7 Weighting for Multistage Designs13.8 Next Steps in WeightingExercises 14 Calibration and Other Uses of Auxiliary Data in Weighting14.1 Weight Calibration14.2 Poststratified and Raking Estimators14.3 GREG and Calibration Estimation14.3.1 Links Between Models, Sample Designs, and Estimators-Special Cases14.3.2 More General Examples14.4 Weight Variability14.4.1 Quantifying the Variability14.4.2 Methods to Limit VariabilityExercises 15 Variance Estimation15.1 Exact Methods15.2 Linear Versus Nonlinear Estimators15.3 Linearization Variance Estimation15.3.1 Estimation Method15.3.2 Confidence Intervals and Degrees of Freedom15.3.3 Accounting for Non-negligible Sampling Fractions15.3.4 Domain Estimation15.3.5 Assumptions and Limitations15.3.6 Special Cases: Poststratification and Quantiles15.3.7 Handling Multiple Weighting Steps with Linearization15.4 Replication15.4.1 Jackknife Replication15.4.2 Balanced Repeated Replication15.4.3 Bootstrap15.5 Combining PSUs or Strata15.5.1 Combining to Reduce the Number of Replicates15.5.2 How Many Groups and Which Strata and PSUs to Combine15.5.3 Combining Strata in One-PSU-per-Stratum Designs15.6 Handling Certainty PSUsExercises 16 Weighting the Personnel Survey: One Solution16.1 The Data Files16.2 Base Weights16.3 Disposition Codes and Mapping into Weighting Categories16.4 Adjustment for Unknown Eligibility16.5 Variables Available for Nonresponse Adjustment16.6 Nonresponse Adjustments16.7 Calibration to Population Counts16.8 Writing Output Files16.9 Example Tabulations Part IV Other Topics17 Multiphase Designs17.1 What is a Multiphase Design?17.2 Examples of Different Multiphase Designs17.2.1 Double Sampling for Stratification17.2.2 Nonrespondent Subsampling17.2.3 Responsive Designs17.2.4 General Multiphase Designs17.3 Survey Weights17.3.1 Base Weights17.3.2 Analysis Weights17.4 Estimation17.4.1 Descriptive Point Estimation17.4.2 Variance Estimation17.4.3 Generalized Regression Estimator (GREG)17.5 Design Choices 17.5.1 Multiphase versus Single Phase 17.5.2 Sample Size Calculations17.6 R SoftwareExercises 18. Non-probability Samples18.1 Types of Non-probability Samples18.2 Potential Problems18.3 Quasi-randomization Approach18.4 Superpopulation Modeling Approach 19 Process Control and Quality Measures19.1 Design and Planning19.2 Quality Control in Frame Creation and Sample Selection19.3 Monitoring Data Collection . . .19.4 Performance Rates and Indicators19.5 Data Editing19.5.1 Editing Disposition Codes19.5.2 Editing the Weighting Variables19.6 Quality Control of Weighting Steps19.7 Specification Writing and Programming19.8 Project Documentation and Archiving Part V. Backmatter Appendix A: Notation GlossaryAppendix B: Data SetsAppendix C: R Functions Used in this Book1 r="" overviewC.2 Author-Defined R FunctionsReferencesSolutions to Selected ExercisesSubject Index
Este título pertence ao(s) assunto(s) indicados(s). Para ver outros títulos clique no assunto desejado.
This book explains approaches long used by survey statisticians, illustrating how existing software can be used to solve survey problems, and developing some specialized software where needed.
PrefaceAcknowledgements 1 An Overview of Sample Design and Weighting1.1 Background and Terminology1.2 Chapter Guide Part I Designing Single-Stage Sample Surveys2 Project 1: Design a Single-Stage Personnel Survey2.1 Specifications for the Study2.2 Questions Posed by the Design Team2.3 Preliminary Analyses2.4 Documentation2.5 Next Steps 3 Sample Design and Sample Size for Single-Stage Surveys 3.1 Determining a Sample Size for a Single-Stage Design 3.1.1 Simple Random Sampling3.1.2 Stratified Simple Random Sampling3.2 Finding Sample Sizes When Sampling with Varying Probabilities 3.2.1 Probability Proportional to Size Sampling3.2.2 Regression Estimates of Totals3.3 Other Methods of Sampling3.4 Estimating Population Parameters from a Sample3.5 Special Topics3.5.1 Rare Characteristics3.5.2 Domain Estimates3.6 More Discussion of Design Effects3.7 Software for Sample Selection3.7.1 R Packages3.7.2 SAS PROC SURVEYSELECTExercises 4 Power Calculations and Sample Size Determination 4.1 Terminology and One-Sample Tests4.2 Power in a One-Sample Test4.3 Two-Sample Tests4.3.1 Differences in Means4.3.2 Differences in Proportions4.3.3 Special Case: Relative Risk4.3.4 Special Case: Effect Sizes4.4 R Power Functions4.5 Power and Sample Size Calculations in SAS. Exercises 5 Mathematical Programming5.1 Multicriteria Optimization5.2 Microsoft Excel Solver5.3 SAS PROC NLP5.4 SAS PROC OPTMODEL5.5 R Alabama Package <6 Outcome Rates and Effect on Sample Size6.1 Disposition Codes6.2 Definitions of Outcome Rates6.3 Sample Units with Unknown AAPOR Classification6.4 Weighted Versus Unweighted Rates6.5 Accounting for Sample Losses in Determining Initial Sample Size6.5.1 Sample Size Inflation Rates at Work6.5.2 ReplicatesExercises 7 The Personnel Survey Design Project: One Solution 7.1 Overview of the Project 7.2 Formulate the Optimization Problem7.2.1 Objective Function 7.2.2 Decision Variables 7.2.3 Optimization Parameters7.2.4 Specified Survey Constraints 7.3 One Solution 7.3.1 Power Analyses7.3.2 Optimization Results7.4 Additional Sensitivity Analysis7.5 Conclusion Part II Multistage Designs 8 Project 2: Designing an Area Sample 9 Designing Multistage Samples 9.1 Types of PSUs 9.2 Basic Variance Results 9.2.1 Two-Stage Sampling 9.2.2 Nonlinear Estimators in Two-Stage Sampling 9.2.3 More General Two-Stage Designs 9.2.4 Three-Stage Sampling 9.3 Cost Functions and Optimal Allocations for Multistage Sampling 9.3.1 Two-Stage Sampling When Numbers of Sample PSUs and Elements per PSU Are Adjustable 9.3.2 Three-Stage Sampling When Sample Sizes Are Adjustable 9.3.3 Two- and Three-Stage Sampling with a Fixed Set of PSUs 9.4 Estimating Measures of Homogeneity and Variance Components9.4.1 Two-Stage Sampling 9.4.2 Three-Stage Sampling 9.4.3 Using Anticipated Variances The lme4 R package has been updated so that the syntax in the 1st edition no longer works. We will revise the examples in this section for the new version of the package.9.5 Stratification of PSUs 9.6 Identifying Certainties Exercises 10 Area Sampling10.1 Census Geographic Units10.2 Census Data and American Community Survey Data10.3 Units at Different Stages of Sampling10.3.1 Primary Sampling Units10.3.2 Secondary Sampling Units10.3.3 Ultimate Sampling Units10.4 Examples of Area Probability Samples10.4.1 Current Population Survey10.4.2 National Survey on Drug Use and Health10.4.3 Panel Arbeitsmarkt und Soziale Sicherung10.5 Composite MOS for Areas10.5.1 Designing the Sample from Scratch10.5.2 Using the Composite MOS with an Existing PSU Sample10.6 Effects of Population Change: The New Construction Issue10.7 Special Address Lists10.7.1 Allocations in ABS using Mathematical Programming Mathematical programming allows efficient allocations to be made to domains (e.g., age groups) using information on housing units that can be purchased from commercial list makers. Discussion and examples will be added to illustrate this technique. The following article will be the basis for examples: Valliant, R., Hubbard, F., Lee, S., Chang, W. (2014). "Efficient Use of Commercial Lists in Household Sampling", Journal of Survey Statistics and Methodology, 2, 182-209.Exercises 11 The Area Sample Design: One Solution Part III Survey Weights and Analyses12 Project 3: Weighting a Personnel Survey 13 Basic Steps in Weighting13.1 Overview of Weighting13.2 Theory of Weighting and Estimation13.3 Base Weights13.4 Adjustments for Unknown Eligibility13.5 Adjustments for Nonresponse13.5.1 Weighting Class Adjustments13.5.2 Propensity Score Adjustments13.5.3 Classification Algorithms13.6 Collapsing Predefined Classes13.7 Weighting for Multistage Designs13.8 Next Steps in WeightingExercises 14 Calibration and Other Uses of Auxiliary Data in Weighting14.1 Weight Calibration14.2 Poststratified and Raking Estimators14.3 GREG and Calibration Estimation14.3.1 Links Between Models, Sample Designs, and Estimators-Special Cases14.3.2 More General Examples14.4 Weight Variability14.4.1 Quantifying the Variability14.4.2 Methods to Limit VariabilityExercises 15 Variance Estimation15.1 Exact Methods15.2 Linear Versus Nonlinear Estimators15.3 Linearization Variance Estimation15.3.1 Estimation Method15.3.2 Confidence Intervals and Degrees of Freedom15.3.3 Accounting for Non-negligible Sampling Fractions15.3.4 Domain Estimation15.3.5 Assumptions and Limitations15.3.6 Special Cases: Poststratification and Quantiles15.3.7 Handling Multiple Weighting Steps with Linearization15.4 Replication15.4.1 Jackknife Replication15.4.2 Balanced Repeated Replication15.4.3 Bootstrap15.5 Combining PSUs or Strata15.5.1 Combining to Reduce the Number of Replicates15.5.2 How Many Groups and Which Strata and PSUs to Combine15.5.3 Combining Strata in One-PSU-per-Stratum Designs15.6 Handling Certainty PSUsExercises 16 Weighting the Personnel Survey: One Solution16.1 The Data Files16.2 Base Weights16.3 Disposition Codes and Mapping into Weighting Categories16.4 Adjustment for Unknown Eligibility16.5 Variables Available for Nonresponse Adjustment16.6 Nonresponse Adjustments16.7 Calibration to Population Counts16.8 Writing Output Files16.9 Example Tabulations Part IV Other Topics17 Multiphase Designs17.1 What is a Multiphase Design?17.2 Examples of Different Multiphase Designs17.2.1 Double Sampling for Stratification17.2.2 Nonrespondent Subsampling17.2.3 Responsive Designs17.2.4 General Multiphase Designs17.3 Survey Weights17.3.1 Base Weights17.3.2 Analysis Weights17.4 Estimation17.4.1 Descriptive Point Estimation17.4.2 Variance Estimation17.4.3 Generalized Regression Estimator (GREG)17.5 Design Choices 17.5.1 Multiphase versus Single Phase 17.5.2 Sample Size Calculations17.6 R SoftwareExercises 18. Non-probability Samples18.1 Types of Non-probability Samples18.2 Potential Problems18.3 Quasi-randomization Approach18.4 Superpopulation Modeling Approach 19 Process Control and Quality Measures19.1 Design and Planning19.2 Quality Control in Frame Creation and Sample Selection19.3 Monitoring Data Collection . . .19.4 Performance Rates and Indicators19.5 Data Editing19.5.1 Editing Disposition Codes19.5.2 Editing the Weighting Variables19.6 Quality Control of Weighting Steps19.7 Specification Writing and Programming19.8 Project Documentation and Archiving Part V. Backmatter Appendix A: Notation GlossaryAppendix B: Data SetsAppendix C: R Functions Used in this Book1 r="" overviewC.2 Author-Defined R FunctionsReferencesSolutions to Selected ExercisesSubject Index
Este título pertence ao(s) assunto(s) indicados(s). Para ver outros títulos clique no assunto desejado.
