Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- PART I INTRODUCTION
- PART II CLASSICAL RANDOMIZED EXPERIMENTS
- 4 A Taxonomy of Classical Randomized Experiments
- 5 Fisher's Exact P-Values for Completely Randomized Experiments
- 6 Neyman's Repeated Sampling Approach to Completely Randomized Experiments
- 7 Regression Methods for Completely Randomized Experiments
- 8 Model-Based Inference for Completely Randomized Experiments
- 9 Stratified Randomized Experiments
- 10 Pairwise Randomized Experiments
- 11 Case Study: An Experimental Evaluation of a Labor Market Program
- PART III REGULAR ASSIGNMENT MECHANISMS: DESIGN
- PART IV REGULAR ASSIGNMENT MECHANISMS: ANALYSIS
- PART V PRGULAR ASSIGNMENT MECHANISMS:SUPPLEMENTARY ANALYSES
- PART VI REGULAR ASSIGNMENT MECHANISMS WITH NONCOMPLIANCE: ANALYSIS
- PART VII CONCLUSION
- References
- Author Index
- Subject Index
11 - Case Study: An Experimental Evaluation of a Labor Market Program
from PART II - CLASSICAL RANDOMIZED EXPERIMENTS
Published online by Cambridge University Press: 05 May 2015
- Frontmatter
- Dedication
- Contents
- Preface
- PART I INTRODUCTION
- PART II CLASSICAL RANDOMIZED EXPERIMENTS
- 4 A Taxonomy of Classical Randomized Experiments
- 5 Fisher's Exact P-Values for Completely Randomized Experiments
- 6 Neyman's Repeated Sampling Approach to Completely Randomized Experiments
- 7 Regression Methods for Completely Randomized Experiments
- 8 Model-Based Inference for Completely Randomized Experiments
- 9 Stratified Randomized Experiments
- 10 Pairwise Randomized Experiments
- 11 Case Study: An Experimental Evaluation of a Labor Market Program
- PART III REGULAR ASSIGNMENT MECHANISMS: DESIGN
- PART IV REGULAR ASSIGNMENT MECHANISMS: ANALYSIS
- PART V PRGULAR ASSIGNMENT MECHANISMS:SUPPLEMENTARY ANALYSES
- PART VI REGULAR ASSIGNMENT MECHANISMS WITH NONCOMPLIANCE: ANALYSIS
- PART VII CONCLUSION
- References
- Author Index
- Subject Index
Summary
INTRODUCTION
In this chapter we illustrate some of the methods discussed in the previous chapters in an application. The application involves a social program designed to improve labor market outcomes for individuals with relatively poor skills and labor market histories: the Saturation Work Initiative Model (SWIM) program in San Diego, evaluated during the period 1985–1987. As is typical, a substantial amount of background information on the individuals in the program was collected, including demographics and recent labor market histories, allowing us to investigate heterogeneity in the effects of the program. The outcomes of interest, post-program earnings and employment records, are either discrete or mixed discrete-continuous, suggesting that constant additive treatment-effect assumptions are typically not plausible.
Using these data we will calculate Fisher exact p-values for sharp null hypotheses and construct Neyman large-sample confidence intervals. We will also discuss, in detail, regression and model-based inferences for various average treatment effects, using the covariates to increase precision as well as to estimate treatment effects for subpopulations. We emphasize the model selection choices and the various other decisions faced by researchers.
THE SAN DIEGO SWIM PROGRAM DATA
SWIM primarily targeted women who were eligible for Aid to Families with Dependent Children (AFDC), with children at least six years old (although, as the summary statistics show, there was a substantial proportion of women with younger children, a small number of men, and some individuals with no children). It was a mandatory program, with fairly strong participation enforcement, and provided a sequence of group job search, unpaid work experience, education, and job skills training. Compared to similar programs in other locations, it had broad coverage, with the intention to reach a wide range of individuals eligible for AFDC, including those who may not have participated in such assistance programs. The average cost of participating in this program was $919 per trainee, paid for by the local authorities.
- Type
- Chapter
- Information
- Causal Inference for Statistics, Social, and Biomedical SciencesAn Introduction, pp. 240 - 254Publisher: Cambridge University PressPrint publication year: 2015