Sampling : Design and Analysis (Hardcover, 3 ed)

1.Introduction Guidance from Samples Populations and Representative Samples Selection Bias Convenience Samples Purposive or Judgment Samples Self-selected Samples Undercoverage Overcoverage Nonresponse What Good are Samples with Selection Bias? Measurement Error Questionnaire Design Sampling and Nonsampling Errors Why Use Sampling? Advantages of Taking a Census Advantages of Taking a Sample Instead of a Census Chapter Summary Exercises 2.Simple Probability Samples Types of Probability Samples Framework for Probability Sampling Simple Random Sampling Sampling Weights Confidence Intervals Using Statistical Software to Analyze Survey Data Determining the Sample Size Systematic Sampling Randomization Theory for Simple Random Sampling* Model-Based Theory for Simple Random Sampling* When Should a Simple Random Sample Be Used? Chapter Summary Exercises 3.Stratified Sampling What is Stratified Sampling? Theory of Stratified Sampling Sampling Weights in Stratified Random Sampling Allocating Observations to Strata Proportional Allocation Optimal Allocation Allocation for Specified Precision within Strata Which Allocation to Use? Determining the Total Sample Size Defining Strata Model-Based Theory for Stratified Sampling* Chapter Summary Exercises 4.Ratio and Regression Estimation Ratio Estimation in Simple Random Sampling Why Use Ratio Estimation? Bias and Mean Squared Error of Ratio Estimators Ratio Estimation with Proportions Ratio Estimation Using Weight Adjustments Advantages of Ratio Estimation Regression Estimation in Simple Random Sampling Estimation in Domains Poststratification Ratio Estimation with Stratified Sampling Model-Based Theory for Ratio and Regression Estimation* A Model for Ratio Estimation A Model for Regression Estimation Differences Between Model-Based and Design-Based Estimators Chapter Summary Exercises 5.Cluster Sampling with Equal Probabilities Notation for Cluster Sampling One-Stage Cluster Sampling Clusters of Equal Sizes: Estimation Clusters of Equal Sizes: Theory Clusters of Unequal Sizes Two-Stage Cluster Sampling Designing a Cluster Sample Choosing the psu Size Choosing Subsampling Sizes Choosing the Sample Size (Number of psus) Systematic Sampling Model-Based Theory for Cluster Sampling* Estimation Using Models Design Using Models Chapter Summary Exercises Contents ix 6. Sampling with Unequal Probabilities Sampling One Primary Sampling Unit One-Stage Sampling with Replacement Selecting Primary Sampling Units Theory of Estimation Designing the Selection Probabilities Weights in Unequal-Probability Sampling with Replacement Two-Stage Sampling with Replacement Unequal-Probability Sampling Without Replacement The Horvitz?Thompson Estimator for One-Stage Sampling Selecting the psus The Horvitz?Thompson Estimator for Two-Stage Sampling Weights in Unequal-Probability Samples Examples of Unequal-Probability Samples Randomization Theory Results and Proofs* Model-Based Inference with Unequal-Probability Samples* Chapter Summary Exercises 7.Complex Surveys Assembling Design Components Building Blocks for Surveys Ratio Estimation in Complex Surveys Simplicity in Survey Design Sampling Weights Constructing Sampling Weights Self-Weighting and Non-Self-Weighting Samples Estimating Distribution Functions and Quantiles Design Effects The National Health and Nutrition Examination Survey Graphing Data from a Complex Survey Univariate Plots Bivariate Plots Chapter Summary Exercises 8.Nonresponse Effects of Ignoring Nonresponse Designing Surveys to Reduce Nonresponse Two-Phase Sampling Response Propensities and Mechanisms for Nonresponse Auxiliary Information for Treating Nonresponse Methods to Adjust for Nonresponse Response Propensities Types of Missing Data Adjusting Weights for Nonresponse Weighting Class Adjustments Regression Models for Response Propensities Poststratification Poststratification Using Weights Raking Adjustments Steps for Constructing Final Survey Weights Advantages and Disadvantages of Weighting Adjustments Imputation Deductive Imputation Cell Mean Imputation Hot-Deck Imputation Regression Imputation and Chained Equations Imputation from Another Data Source Multiple Imputation Advantages and Disadvantages of Imputation Response Rates and Nonresponse Bias Calculating and Reporting Response Rates What is an Acceptable Response Rate? Nonresponse Bias Assessments Chapter Summary Exercises 9.Variance Estimation in Complex Surveys Linearization (Taylor Series) Methods Random Group Methods Replicating the Survey Design Dividing the Sample into Random Groups Resampling and Replication Methods Balanced Repeated Replication (BRR) Jackknife Bootstrap Creating and Using Replicate Weights Generalized Variance Functions Confidence Intervals Confidence Intervals for Smooth Functions of Population Totals Confidence Intervals for Population Quantiles Chapter Summary Exercises 10.Categorical Data Analysis in Complex Surveys Chi-Square Tests with Multinomial Sampling Testing Independence of Factors Testing Homogeneity of Proportions Testing Goodness of Fit Effects of Survey Design on Chi-Square Tests Contingency Tables for Data from Complex Surveys Effects on Hypothesis Tests and Confidence Intervals Corrections to Chi-Square Tests Wald Tests Rao?Scott Tests Model-Based Methods for Chi-Square Tests Loglinear Models Loglinear Models with Multinomial Sampling Loglinear Models in a Complex Survey Chapter Summary Exercises 11.Regression in Complex Surveys Model-Based Regression in Simple Random Samples Regression with Complex Survey Data Point Estimation Standard Errors Multiple Regression Regression Using Weights versus Weighted Least Squares Using Regression to Compare Domain Means Interpreting Regression Coefficients from Survey Data Purposes of Regression Analyses Model-Based and Design-Based Inference Survey Weights and Regression Survey Design and Standard Errors Mixed Models for Cluster Samples Logistic Regression Calibration to Population Totals Chapter Summary Exercises 12.Two-Phase Sampling Theory for Two-Phase Sampling Two-Phase Sampling with Stratification Ratio and Regression Estimation in Two-Phase Samples Two-Phase Sampling with Ratio Estimation Generalized Regression Estimation in Two-Phase Sampling Jackknife Variance Estimation for Two-Phase Sampling Designing a Two-Phase Sample Two-Phase Sampling with Stratification Optimal Allocation for Ratio Estimation Chapter Summary Exercises 13.Estimating the Size of a Population Capture?Recapture Estimation Contingency Tables for Capture?Recapture Experiments Confidence Intervals for N Using Capture?Recapture on Lists Multiple Recapture Estimation Chapter Summary Exercises 14.Rare Populations and Small Area Estimation Sampling Rare Populations Stratified Sampling with Disproportional Allocation Two-Phase Sampling Unequal-Probability Sampling Multiple Frame Surveys Network or Multiplicity Sampling Snowball Sampling Sequential Sampling Small Area Estimation Direct Estimators Synthetic and Composite Estimators Model-based Estimators Chapter Summary Exercises 15.Nonprobability Samples Types of Nonprobability Samples Administrative Records Quota Samples Judgment Samples Convenience Samples Selection Bias and Mean Squared Error Random Variables Describing Participation in a Sample Bias and Mean Squared Error of a Sample Mean Reducing Bias of Estimates from Nonprobability Samples Weighting Estimate the Values of the Missing Units Measures of Uncertainty for Nonprobability Samples Nonprobability vs Low-response Probability Samples Chapter Summary Exercises 16.Survey Quality Coverage Error Measuring Coverage and Coverage Bias Coverage and Survey Mode Improving Coverage Nonresponse Error Measurement Error Measuring and Modeling Measurement Error Reducing Measurement Error Sensitive Questions Randomized Response Processing Error Total Survey Quality Chapter Summary Exercises A Probability Concepts Used in Sampling A Probability A Simple Random Sampling with Replacement A Simple Random Sampling without Replacement A Random Variables and Expected Value A Conditional Probability A Conditional Expectation A Exercises