Instrument-based estimation with binarised treatments: issues and tests for the exclusion restriction

Andresen, Martin Eckhoff; Huber, Martin

doi:10.1093/ectj/utab002

Cited by 19 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study has been revisited by many papers, including Tan (2006), Huber and Mellace (2015), Kitagawa (2015), Mourifié and Wan (2017), Andresen and Huber (2021), Słoczyński (2021), and Blandhol et al (2022. Most of these papers focus on binarized versions of Card (1995)'s main endogenous explanatory variable of interest.…”

Section: Causal Effects Of College Educationmentioning

confidence: 99%

Abadie's Kappa and Weighting Estimators of the Local Average Treatment Effect

Słoczyński¹,

Uysal²,

Wooldridge³

2022

Preprint

View full text Add to dashboard Cite

In this paper we study the finite sample and asymptotic properties of various weighting estimators of the local average treatment effect (LATE), several of which are based on Abadie (2003)'s kappa theorem. Our framework presumes a binary endogenous explanatory variable ("treatment") and a binary instrumental variable, which may only be valid after conditioning on additional covariates. We argue that one of the Abadie estimators, which we show is weight normalized, is likely to dominate the others in many contexts. A notable exception is in settings with one-sided noncompliance, where certain unnormalized estimators have the advantage of being based on a denominator that is bounded away from zero. We use a simulation study and three empirical applications to illustrate our findings. In applications to causal effects of college education using the college proximity instrument (Card, 1995) and causal effects of childbearing using the sibling sex composition instrument (Angrist and Evans, 1998), the unnormalized estimates are clearly unreasonable, with "incorrect" signs, magnitudes, or both. Overall, our results suggest that (i) the relative performance of different kappa weighting estimators varies with features of the data-generating process; and that (ii) the normalized version of Tan (2006)'s estimator may be an attractive alternative in many contexts. Applied researchers with access to a binary instrumental variable should also consider covariate balancing or doubly robust estimators of the LATE.

show abstract

Section: Causal Effects Of College Educationmentioning

confidence: 99%

Abadie's Kappa and Weighting Estimators of the Local Average Treatment Effect

Słoczyński¹,

Uysal²,

Wooldridge³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The consequences of aggregating heterogeneous causal effects have also been discussed in the context of instrumental variables estimation (e.g. Angrist & Imbens, 1995;Marshall, 2016;Andresen & Huber, 2021). While the above papers discuss the consequences of (dis)aggregated treatments for unconditional causal effects, we focus on effect heterogeneity and the additional complications arising there.…”

Section: Related Literaturementioning

confidence: 99%

Effect or Treatment Heterogeneity? Policy Evaluation with Aggregated and Disaggregated Treatments

Heiler¹,

Knaus²

2021

Preprint

View full text Add to dashboard Cite

Binary treatments in empirical practice are often (i) ex-post aggregates of multiple treatments or (ii) can be disaggregated into multiple treatment versions after assignment. In such cases it is unclear whether estimated heterogeneous effects are driven by effect heterogeneity or by treatment heterogeneity. This paper provides estimands to decompose canonical effect heterogeneity into the effect heterogeneity driven by different responses to underlying multiple treatments and potentially different compositions of these underlying effective treatments. This allows to avoid spurious discovery of heterogeneous effects, to detect potentially masked heterogeneity, and to evaluate the underlying assignment mechanism of treatment versions. A nonparametric method for estimation and statistical inference of the decomposition parameters is proposed. The framework allows for the use of machine learning techniques to adjust for high-dimensional confounding of the effective treatments. It can be used to conduct simple joint hypothesis tests for effect heterogeneity that consider all effective treatments simultaneously and circumvent multiple testing procedures. It requires weaker overlap assumptions compared to conventional multi-valued treatment effect analysis. The method is applied to a reevaluation of heterogeneous effects of smoking on birth weight. We find that parts of the differences between ethnic and age groups can be explained by different smoking intensities. We further reassess the gender gap in the effectiveness of the Job Corps training program and find that it is largely explained by gender differences in the type of vocational training received.

show abstract

“…As we show in Appendix B, these moment inequalities are equivalent to the ones in Proposition 4. Andresen and Huber (2021) also state that these conditions should apply conditional on each value of the outcome.…”

Section: Testable Implications Of Emcomentioning

confidence: 99%

“…To test both sets of restrictions, we utilize tools from the moment inequality literature for inference that is well-suited to settings where the number of moment restrictions may exceed the number of observations (Romano et al, 2014;Chernozhukov et al, 2018;Bai et al, 2019). Andresen and Huber (2021) show similar restrictions on treatment distributions must hold when "binarizing" an ordered treatment at a given threshold. Our results build on theirs by deriving novel identification and choice modeling implications of EMCO, which binarzies treatment around zero, and showing how incorporating restrictions on outcome densities can increase power to detect violations.…”

Section: Introductionmentioning

confidence: 99%

On Recoding Ordered Treatments as Binary Indicators

Rose¹,

Shem-Tov²

2021

Preprint

View full text Add to dashboard Cite

Researchers using instrumental variables to investigate the effects of ordered treatments (e.g., years of education, months of healthcare coverage) often recode treatment into a binary indicator for any exposure (e.g., any college, any healthcare coverage). The resulting estimand is difficult to interpret unless the instruments only shift compliers from no treatment to some positive quantity and not from some treatment to more-i.e., there are extensive margin compliers only (EMCO). When EMCO holds, recoded endogenous variables capture a weighted average of treatment effects across complier groups that can be partially unbundled into each group's treated and untreated means. Invoking EMCO along with the standard Local Average Treatment Effect assumptions is equivalent to assuming choices are determined by a simple two-factor selection model in which agents first decide whether to participate in treatment at all and then decide how much. The instruments must only impact relative utility in the first step. Although EMCO constrains unobserved counterfactual choices, it places testable restrictions on the joint distribution of outcomes, treatments, and instruments.

show abstract

Instrument-based estimation with binarised treatments: issues and tests for the exclusion restriction

Cited by 19 publications

References 38 publications

Abadie's Kappa and Weighting Estimators of the Local Average Treatment Effect

Abadie's Kappa and Weighting Estimators of the Local Average Treatment Effect

Effect or Treatment Heterogeneity? Policy Evaluation with Aggregated and Disaggregated Treatments

On Recoding Ordered Treatments as Binary Indicators

Contact Info

Product

Resources

About