Nonparametric Tests for Treatment Effect Heterogeneity

Crump, Richard K.; Hotz, V. Joseph; Imbens, Guido W.; Mitnik, Oscar A.

doi:10.3386/t0324

Cited by 94 publications

(149 citation statements)

References 42 publications

Supporting

Mentioning

148

Contrasting

Unclassified

Order By: Relevance

“…Systematic tests on whether the results differ across sites will be needed. The insights of the literature on heterogeneous treatment effects, which we discuss below, can be applied here: First, the different site dummies can be treated as covariates in a pooled regression; nonparametric tests of heterogeneity (e.g., Crump et al 2009) can be performed. If heterogeneity is found, a more powerful test would be whether heterogeneity still remains after accounting for the heterogeneity of the covariates.…”

Section: Environmental Dependencementioning

confidence: 99%

“…Crump et al (2009) developed two nonparametric tests of whether heterogeneity is present in treatment effects: one to determine whether the treatment effect is zero for any subpopulation (defined by covariates) and another for whether the treatment effect is the same for all subpopulations (defined by covariates). Heckman et al (2006) and Heckman & Vytlacil (2008a,b) discuss the implication of treatment heterogeneity in terms of both observable and nonobservables.…”

Section: Heterogeneity In Treatment Effectsmentioning

confidence: 99%

See 1 more Smart Citation

The Experimental Approach to Development Economics

2009

View full text Add to dashboard Cite

Randomized experiments have become a popular tool in development economics research and have been the subject of a number of criticisms. This paper reviews the recent literature and discusses the strengths and limitations of this approach in theory and in practice. We argue that the main virtue of randomized experiments is that, owing to the close collaboration between researchers and implementers, they allow the estimation of parameters that would not otherwise be possible to evaluate. We discuss the concerns that have been raised regarding experiments and generally conclude that, although real, they are often not specific to experiments. We conclude by discussing the relationship between theory and experiments.

show abstract

Section: Environmental Dependencementioning

confidence: 99%

Section: Heterogeneity In Treatment Effectsmentioning

confidence: 99%

The Experimental Approach to Development Economics

2009

View full text Add to dashboard Cite

show abstract

“…For example, Crump, Hotz, Imbens & Mitnik (2008) develop convenient nonparametric tests of the null hypothesis that average treatment effects are zero, or non-zero but constant, across subgroups. By comparison, we test the null hypothesis of constant within-group treatment effects while allowing average treatment effects to vary arbitrarily across subgroups.…”

Section: Introductionmentioning

confidence: 99%

Can Variation in Subgroups' Average Treatment Effects Explain Treatment Effect Heterogeneity? Evidence from a Social Experiment

Bitler

Gelbach

Hoynes

2014

View full text Add to dashboard Cite

In this paper, we assess whether welfare reform affects earnings only through mean impacts that are constant within but vary across subgroups. This is important because researchers interested in treatment effect heterogeneity typically restrict their attention to estimating mean impacts that are only allowed to vary across subgroups. Using a novel approach to simulating treatment group earnings under the constant mean-impacts within subgroup model, we find that this model does a poor job of capturing the treatment effect heterogeneity for Connecticut's Jobs First welfare reform experiment using quantile treatment effects. Notably, ignoring within-group heterogeneity would lead one to miss evidence that the Jobs First experiment's effects are consistent with central predictions of basic labor supply theory.

show abstract

“…Only the work in Thailand and Costa Rica (10,11,13) also included information on environmental outcomes. However, those previous studies do not include sufficiently detailed analysis of heterogeneity in impacts to assess potential tradeoffs between ecosystem protection and poverty alleviation (15,16).…”

mentioning

confidence: 99%

Conditions associated with protected area success in conservation and poverty reduction

Ferraro

Hanauer²,

Sims³

2011

Proc. Natl. Acad. Sci. U.S.A.

233

172

View full text Add to dashboard Cite

Protected areas are the dominant approach to protecting biodiversity and the supply of ecosystem services. Because these protected areas are often placed in regions with widespread poverty and because they can limit agricultural development and exploitation of natural resources, concerns have been raised about their potential to create or reinforce poverty traps. Previous studies suggest that the protected area systems in Costa Rica and Thailand, on average, reduced deforestation and alleviated poverty. We examine these results in more detail by characterizing the heterogeneity of responses to protection conditional on observable characteristics. We find no evidence that protected areas trap historically poorer areas in poverty. In fact, we find that poorer areas at baseline seem to have the greatest levels of poverty reduction as a result of protection. However, we do find that the spatial characteristics associated with the most poverty alleviation are not necessarily the characteristics associated with the most avoided deforestation. We show how an understanding of these spatially heterogeneous responses to protection can be used to generate suitability maps that identify locations in which both environmental and poverty alleviation goals are most likely to be achieved.

show abstract

Nonparametric Tests for Treatment Effect Heterogeneity

Cited by 94 publications

References 42 publications

The Experimental Approach to Development Economics

The Experimental Approach to Development Economics

Can Variation in Subgroups' Average Treatment Effects Explain Treatment Effect Heterogeneity? Evidence from a Social Experiment

Conditions associated with protected area success in conservation and poverty reduction

Contact Info

Product

Resources

About