Micro-econometrics for policy, program, and treatment effects / Myoung-jae Lee.

Format:

Book

Author/Creator:

Lee, Myoung-jae.

Series:

Advanced texts in econometrics.

Advanced texts in econometrics

Language:

English

Subjects (All):

Econometrics.

Econometric models.

Economic policy--Mathematical models.

Economic policy.

Multivariate analysis.

Physical Description:

1 online resource (263 p.)

Place of Publication:

Oxford ; New York : Oxford University Press, 2005.

Language Note:

English

Summary:

Focusing on non-experimental microeconometric estimation, this work provides literature on how to measure accurately the effects of a treatment, such as a drug, educational programme or tax regime, on a response variable like an illness, GPA, or income.

Contents:

Contents; 1 Tour of the book; 2 Basics of treatment effect analysis; 2.1 Treatment intervention, counter-factual, and causal relation; 2.1.1 Potential outcomes and intervention; 2.1.2 Causality and association; 2.1.3 Partial equilibrium analysis and remarks; 2.2 Various treatment effects and no effects; 2.2.1 Various effects; 2.2.2 Three no-effect concepts; 2.2.3 Further remarks; 2.3 Group-mean difference and randomization; 2.3.1 Group-mean difference and mean effect; 2.3.2 Consequences of randomization; 2.3.3 Checking out covariate balance

2.4 Overt bias, hidden (covert) bias, and selection problems2.4.1 Overt and hidden biases; 2.4.2 Selection on observables and unobservables; 2.4.3 Linear models and biases; 2.5 Estimation with group mean difference and LSE; 2.5.1 Group-mean difference and LSE; 2.5.2 A job-training example; 2.5.3 Linking counter-factuals to linear models; 2.6 Structural form equations and treatment effect; 2.7 On mean independence and independence*; 2.7.1 Independence and conditional independence; 2.7.2 Symmetric and asymmetric mean-independence; 2.7.3 Joint and marginal independence

2.8 Illustration of biases and Simpson's Paradox*2.8.1 Illustration of biases; 2.8.2 Source of overt bias; 2.8.3 Simpson's Paradox; 3 Controlling for covariates; 3.1 Variables to control for; 3.1.1 Must cases; 3.1.2 No-no cases; 3.1.3 Yes/no cases; 3.1.4 Option case; 3.1.5 Proxy cases; 3.2 Comparison group and controlling for observed variables; 3.2.1 Comparison group bias; 3.2.2 Dimension and support problems in conditioning; 3.2.3 Parametric models to avoid dimension and support problems; 3.2.4 Two-stage method for a semi-linear model*

3.3 Regression discontinuity design (RDD) and before-after (BA)3.3.1 Parametric regression discontinuity; 3.3.2 Sharp nonparametric regression discontinuity; 3.3.3 Fuzzy nonparametric regression discontinuity; 3.3.4 Before-after (BA); 3.4 Treatment effect estimator with weighting*; 3.4.1 Effect on the untreated; 3.4.2 Effects on the treated and on the population; 3.4.3 Effciency bounds and effcient estimators; 3.4.4 An empirical example; 3.5 Complete pairing with double sums*; 3.5.1 Discrete covariates; 3.5.2 Continuous or mixed (continuous or discrete) covariates; 3.5.3 An empirical example

4 Matching4.1 Estimators with matching; 4.1.1 Effects on the treated; 4.1.2 Effects on the population; 4.1.3 Estimating asymptotic variance; 4.2 Implementing matching; 4.2.1 Decisions to make in matching; 4.2.2 Evaluating matching success; 4.2.3 Empirical examples; 4.3 Propensity score matching; 4.3.1 Balancing observables with propensity score; 4.3.2 Removing overt bias with propensity-score; 4.3.3 Empirical examples; 4.4 Matching for hidden bias; 4.5 Difference in differences (DD); 4.5.1 Mixture of before-after and matching; 4.5.2 DD for post-treatment treated in no-mover panels

4.5.3 DD with repeated cross-sections or panels with movers

Notes:

Description based upon print version of record.

Includes bibliographical references (p. 233-243) and index.

Description based on print version record.

Description based on publisher supplied metadata and other sources.

ISBN:

1-4356-2264-2

9786611198299

1-281-19829-3

0-19-926768-5

0-19-153316-5

OCLC:

77016974