I Preliminaries
1. Overview
1.1 Introduction
1.2 Distinctive Aspects of Microeconometrics
1.3 Book Outline
1.4 How to Use This Book
1.5 Software
1.6 Notation and Conventions
2. Causal and Noncausal Models
2.1 Introduction
2.2 Structural Models
2.3 Exogeneity
2.4 Linear Simultaneous Equations Model
2.5 Identification Concepts
2.6 Single-Equation Models
2.7 Potential Outcome Model
2.8 Causal Modeling and Estimation Strategies
2.9 Bibliographic Notes
3. Microeconomic Data Structures
3.1 Introduction
3.2 Observational Data
3.3 Data from Social Experiments
3.4 Data from Natural Experiments
3.5 Practical Considerations
3.6 Bibliographic Notes
II Core Methods
4. Linear models
4.1 Introduction
4.2 Regressions and Loss Functions
4.3 Example: Returns to Schooling
4.4 Ordinary Least Squares
4.5 Weighted Least Squares
4.6 Median and Quantile Regression
4.7 Model Misspecification
4.8 Instrumental Variables
4.9 Instrumental Variables in Practice
4.10 Practical Considerations
4.11 Bibliographic Notes
5. Maximum Likelihood and Nonlinear Least-Squares Estimation
5.1 Introduction
5.2 Overview of Nonlinear Estimators
5.3 Extremum Estimators
5.4 Estimating Equations
5.5 Statistical Inference
5.6 Maximum Likelihood
5.7 Quasi-Maximum Likelihood
5.8 Nonlinear Least Squares
5.9 Example: ML and NLS Estimation
5.10 Practical Considerations
5.11 Bibliographic Notes
6. Generalized Method of Movements and Systems Estimation
6.1 Introduction
6.2 Examples
6.3 Generalized Method of Moments
6.4 Linear Instrumental Variables
6.5 Nonlinear Instrumental Variables
6.6 Sequential Two-Step m-Estimation
6.7 Minimum Distance Estimation
6.8 Empirical Likelihood
6.9 Linear Systems of Equations
6.10 Nonlinear Sets of Equations
6.11 Practical Considerations
6.12 Bibliographic Notes
7. Hypothesis Tests
7.1 Introduction
7.2 Wald Test
7.3 Likelihood-Based Tests
7.4 Example: Likelihood-Based Hypothesis Tests
7.5 Tests in Non-ML Settings
7.6 Power and Size of Tests
7.7 Monte Carlo Studies
7.8 Bootstrap Example
7.9 Practical Considerations
7.10 Bibliographic Notes
8. Specification Tests and Model Selection
8.1 Introduction
8.2 m-Tests
8.3 Hausman Test
8.4 Tests for Some Common Misspecifications
8.5 Discriminating between Nonnested Models
8.6 Consequences of Testing
8.7 Model Diagnostics
8.8 Practical Considerations
8.9 Bibliographic Notes
9. Semiparametric Methods
9.1 Introduction
9.2 Nonparametric Example: Hourly Wage
9.3 Kernel Density Estimation
9.4 Nonparametric Local Regression
9.5 Kernel Regression
9.6 Alternative Nonparametric Regression Estimators
9.7 Semiparametric Regression
9.8 Derivations of Mean and Variance of Kernel Estimators
9.9 Practical Considerations
9.10 Bibliographic Notes
10. Numerical Optimization
10.1 Introduction
10.2 General Considerations
10.3 Specific Methods
10.4 Practical Considerations
10.5 Bibliographic Notes
III Simulation-based methods
11. Bootstrap Methods
11.1 Introduction
11.2 Bootstrap Summary
11.3 Bootstrap Example
11.4 Bootstrap Theory
11.5 Bootstrap Extensions
11.6 Bootstrap Applications
11.7 Practical Considerations
11.8 Bibliographic Notes
12. Simulation-Based Methods
12.1 Introduction
12.2 Examples
12.3 Basics of Computing Integrals
12.4 Maximum Simulated Likelihood Estimation
12.5 Moment-Based Simulation Estimation
12.6 Indirect Inference
12.7 Simulators
12.8 Methods of Drawing Random Variates
12.9 Bibliographic Notes
13. Bayesian Methods
13.1 Introduction
13.2 Bayesian Approach
13.3 Bayesian Analysis of Linear Regression
13.4 Monte Carlo Integration
13.5 Markov Chain Monte Carlo Simulation
13.6 MCMC Example: Gibbs Sampler for SUR
13.7 Data Augmentation
13.8 Bayesian Model Selection
13.9 Practical Considerations
13.10 Bibliographic Notes
IV Models for Cross-Section Data
14. Binary Outcome Models
14.1 Introduction
14.2 Binary Outcome Example: Fishing Mode Choice
14.3 Logit and Probit Models
14.4 Latent Variable Models
14.5 Choice-Based Samples
14.6 Grouped and Aggregate Data
14.7 Semiparametric Estimation
14.8 Derivation of Logit from Type I Extreme Value
14.9 Practical Considerations
14.10 Bibliographic Notes
15. Multinomial Models
15.1 Introduction
15.2 Example: Choice of Fishing Mode
15.3 General Results
15.4 Multinomial Logit
15.5 Additive Random Utility Models
15.6 Nested Logit
15.7 Random Parameters Logit
15.8 Multinomial Probit
15.9 Ordered, Sequential, and Ranked Outcomes
15.10 Multivariate Discrete Outcomes
15.11 Semiparametric Estimation
15.12 Derivations for MNL, CL, and NL Models
15.13 Practical Considerations
15.14 Bibliographic Notes
16. Tobit and Selection Models
16.1 Introduction
16.2 Censored and Truncated Models
16.3 Tobit Model
16.4 Two-Part Model
16.5 Sample Selection Models
16.6 Selection Example: Health Expenditures
16.7 Roy Model
16.8 Structural Models
16.9 Semiparametric Estimation
16.10 Derivations for the Tobit Model
16.11 Practical Considerations
16.12 Bibliographic Notes
17. Transition Data: Survival Analysis
17.1 Introduction
17.2 Example: Duration of Strikes
17.3 Basic Concepts
17.4 Censoring
17.5 Nonparametric Models
17.6 Parametric Regression Models
17.7 Some Important Duration Models
17.8 Cox PH Model
17.9 Time-Varying Regressors
17.10 Discrete-Time Proportional Hazards
17.11 Duration Example: Unemployment Duration
17.12 Practical Considerations
17.13 Bibliographic Notes
18. Mixture Models and Unobserved Heterogeneity
18.1 Introduction
18.2 Unobserved Heterogeneity and Dispersion
18.3 Identification in Mixture Models
18.4 Specification of the Heterogeneity Distribution
18.5 Discrete Heterogeneity and Latent Class Analysis
18.6 Stock and Flow Sampling
18.7 Specification Testing
18.8 Unobserved Heterogeneity Example: Unemployment Duration
18.9 Practical Considerations
18.10 Bibliographic Notes
19. Models of Multiple Hazards
19.1 Introduction
19.2 Competing Risks
19.3 Joint Duration Distributions
19.4 Multiple Spells
19.5 Competing Risks Example: Unemployment Duration
19.6 Practical Considerations
19.7 Bibliographic Notes
20. Models of Count Data
20.1 Introduction
20.2 Basic Count Data Regression
20.3 Count Example: Contacts with Medical Doctor
20.4 Parametric Count Regression Models
20.5 Partially Parametric Models
20.6 Multivariate Counts and Endogenous Regressors
20.7 Count Example: Further Analysis
20.8 Practical Considerations
20.9 Bibliographic Notes
V Models for Panel Data
21. Linear Panel Models: Basics
21.1 Introduction
21.2 Overview of Models and Estimators
21.3 Linear Panel Example: Hours and Wages
21.4 Fixed Effects versus Random Effects Models
21.5 Pooled Models
21.6 Fixed Effects Model
21.7 Random Effects Model
21.8 Modeling Issues
21.9 Practical Considerations
21.10 Bibliographic Notes
22. Linear Panel Models: Extensions
22.1 Introduction
22.2 GMM Estimation of Linear Panel Models
22.3 Panel GMM Example: Hours and Wages
22.4 Random and Fixed Effects Panel GMM
22.5 Dynamic Models
22.6 Difference-in-Differences Estimator
22.7 Repeated Cross Sections and Pseudo Panels
22.8 Mixed Linear Models
22.9 Practical Considerations
22.10 Bibliographic Notes
23. Nonlinear Panel Models
23.1 Introduction
23.2 General Results
23.3 Nonlinear Panel Example: Patents and R&D
23.4 Binary Outcome Data
23.5 Tobit and Selection Models
23.6 Transition Data
23.7 Count Data
23.8 Semiparametric Estimation
23.9 Practical Considerations
23.10 Bibliographic Notes
VI Further Topics
24. Stratified and Clustered Samples
24.1 Introduction
24.2 Survey Sampling
24.3 Weighting
24.4 Endogenous Stratification
24.5 Clustering
24.6 Hierarchical Linear Models
24.7 Clustering Example: Vietnam Health Care Use
24.8 Complex Surveys
24.9 Practical Considerations
24.10 Bibliographic Notes
25. Treatment Evaluation
25.1 Introduction
25.2 Setup and Assumptions
25.3 Treatment Effects and Selection Bias
25.4 Matching and Propensity Score Estimators
25.5 Differences-in-Differences Estimators
25.6 Regression Discontinuity Design
25.7 Instrumental Variable Methods
25.8 Example: The Effect of Training on Earnings
25.9 Bibliographic Notes
26. Measurement Error Models
26.1 Introduction
26.2 Measurement Error in Linear Regression
26.3 Identification Strategies
26.4 Measurement Errors in Nonlinear Models
26.5 Attenuation Bias Simulation Examples
26.6 Bibliographic Notes
27. Missing Data and Imputation
27.1 Introduction
27.2 Missing Data Assumptions
27.3 Handling Missing Data without Models
27.4 Observed-Data Likelihood
27.5 Regression-Based Imputation
27.6 Data Augmentation and MCMC
27.7 Multiple Imputation
27.8 Missing Data MCMC Imputation Example
27.9 Practical Considerations
27.10 Bibliographic Notes
Appendices
A. Asymptotic Theory
A.1 Introduction
A.2 Convergence in Probability
A.3 Laws of Large Numbers
A.4 Convergence in Distribution
A.5 Central Limit Theorems
A.6 Multivariate Normal Limit Distributions
A.7 Stochastic Order of Magnitude
A.8 Other Results
A.9 Bibliographic Notes
B. Making Pseudo-Random Draws
References
Index
