Choosing Among Alternative Nonexperimental Methods for Estimating the Impact of Social Programs: The Case of Manpower Training

Heckman, James J.; Hotz, V. Joseph

doi:10.2307/2290059

Cited by 441 publications

(301 citation statements)

References 9 publications

Supporting

Mentioning

289

Contrasting

Unclassified

Order By: Relevance

“…These and other studies reported in the literature more than 20 years ago fueled the flight of many empirical economists from structural models, even though Heckman and Hotz (1989) cautioned that many applications of the structural approach by those comparing structural estimates with experimental estimates did not perform specification tests to see if the estimated structural models were concordant with the pre-program data. They show that when such tests are performed, the surviving structural models closely match the estimates produced from the experiment analyzed by LaLonde, findings duplicated for other experiments (see Todd and Wolpin, 2006, Attanasio, Meghir, and Santiago, 2009, Attanasio, Meghir, and Santiago, 2009, and the discussion in Keane, Todd, and Wolpin, 2010).…”

Section: Introductionmentioning

confidence: 99%

Building Bridges between Structural and Program Evaluation Approaches to Evaluating Policy

Heckman

2010

Journal of Economic Literature

290

View full text Add to dashboard Cite

This paper compares the structural approach to economic policy analysis with the program evaluation approach. It offers a third way to do policy analysis that combines the best features of both approaches. We illustrate the value of this alternative approach by making the implicit economics of LATE explicit, thereby extending the interpretability and range of policy questions that LATE can answer.

show abstract

Section: Introductionmentioning

confidence: 99%

Building Bridges between Structural and Program Evaluation Approaches to Evaluating Policy

Heckman

2010

Journal of Economic Literature

290

View full text Add to dashboard Cite

show abstract

“…27 It is for this reason that the similarity of pre-intervention trends in outcomes is often considered a necessary but insufficient condition for the validity of DiD methods. 28 The notable contributions in this area are all from the US: see Heckman and Hotz (1989), Friedlander and Robins (1995), Heckman and Smith (1995), Lalonde (1986), and Dehejia and Wahba (1999). 29 For more information, see http://www.ifs.org.uk/centres/ PEPA.…”

Section: Resultsmentioning

confidence: 99%

Time-Limited in-Work Benefits in the UK: A Review of Recent Evidence

Chowdry

2012

Natl. Inst. econ. rev.

View full text Add to dashboard Cite

This paper reviews three UK-based welfare-to-work programmes featuring time-limited financial incentives to leave out-ofwork benefits for employment. The policies considered are (i) the Employment Retention and Advancement demonstration, aimed at lone parents and the long-term unemployed; (ii) In-Work Credit, aimed at lone parents on welfare; (iii) Pathways to Work, aimed at recipients of incapacity benefits. I illustrate the difficulties in extrapolating from specific findings to general policy-relevant conclusions. Finally, I depict the challenge facing evaluators in future and point to the directions in which evaluation will need to develop if it is to contribute more fully to policy-relevant evaluation.

show abstract

“…Goldberger (1972) was the first to consider a similar situation and argued that researchers should be cautious in interpreting the impact of a social program due to a potential bias. Heckman and Hotz ( 1989) show that when assignment to probation is nonrandom, &dquo;selection bias&dquo; in the estimation of a in Equation 1 can arise due to dependence between d, and u,. In other words, selection bias is present if And consequently, A stochastic relationship between d, and u,, of course, can arise for a variety of reasons.…”

Section: Correcting Selection and Censoring Biasesmentioning

confidence: 95%

An Econometric Study On the Deterrent Impact of Probation

Kim

1994

Eval Rev

View full text Add to dashboard Cite

A drug offenders data set, recently collected in Florida, is used to estimate the impact of probation, vis-à-vis imprisonment, on recidivism. Because the sample period is characterized as "getting tough on drugs, " a possible connection between the drug policy and the deterrent impact of probation is explored. Econometrically, the main concern of this article is to correct not only the bias related to the selection process, but the bias resulting from interruption of the duration variable of those who have not returned to prison by the end of the survey. After employing methodologies to correct for these biases, there remains no evidence that probation per se has any significant impact on the duration of recidivism. ample selection bias occurs if the selection of program participants is not made randomly.' The nonrandomness results either from participants themselves or from selective screening by program administrators. In both cases, the program participants may share common attributes that may or may not be observable. Nevertheless, sharing similar attributes clearly becomes a main source of bias if the shared attributes are ignored when postprogram performance is evaluated. Under such circumstances, evaluation of the program may be an evaluation of the attributes of the program participants.2

show abstract

Choosing Among Alternative Nonexperimental Methods for Estimating the Impact of Social Programs: The Case of Manpower Training

Cited by 441 publications

References 9 publications

Building Bridges between Structural and Program Evaluation Approaches to Evaluating Policy

Building Bridges between Structural and Program Evaluation Approaches to Evaluating Policy

Time-Limited in-Work Benefits in the UK: A Review of Recent Evidence

An Econometric Study On the Deterrent Impact of Probation

Contact Info

Product

Resources

About