2014
DOI: 10.1080/07350015.2014.888290
|View full text |Cite
|
Sign up to set email alerts
|

Testing the Unconfoundedness Assumption via Inverse Probability Weighted Estimators of (L)ATT

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
42
0

Year Published

2014
2014
2024
2024

Publication Types

Select...
6
2

Relationship

2
6

Authors

Journals

citations
Cited by 52 publications
(42 citation statements)
references
References 25 publications
0
42
0
Order By: Relevance
“…(), Abadie (, 2003), Frölich () and Donald et al. (, ), the LATE is defined as LATEfalse(xsfalse)Efalse[Y(1)Y(0)false|Xs=xs,scriptCfalse], where scriptC denotes the group of compliers and the null hypothesis of interest is defined as H0italiclate:LATEfalse(xsfalse)0,for all xsscriptXs. It is well known that LATE(xs) is identified by LATEfalse(xfalse)=E[]ZYq(X)(1Z)Y1q(X)|Xs=xs/E[]ZDq(X)(1Z)D1q(X)|Xs=xs,where q(x)=P(Z=1|X=x).…”
Section: Extensionsmentioning
confidence: 99%
See 1 more Smart Citation
“…(), Abadie (, 2003), Frölich () and Donald et al. (, ), the LATE is defined as LATEfalse(xsfalse)Efalse[Y(1)Y(0)false|Xs=xs,scriptCfalse], where scriptC denotes the group of compliers and the null hypothesis of interest is defined as H0italiclate:LATEfalse(xsfalse)0,for all xsscriptXs. It is well known that LATE(xs) is identified by LATEfalse(xfalse)=E[]ZYq(X)(1Z)Y1q(X)|Xs=xs/E[]ZDq(X)(1Z)D1q(X)|Xs=xs,where q(x)=P(Z=1|X=x).…”
Section: Extensionsmentioning
confidence: 99%
“…Second, we extend our test for the null hypothesis that the conditional stochastic dominance relation between the potential outcomes holds for all values of the subset of the covariates. Last, we extend our test to cases where the treatment assignment is endogenous, as in the local average treatment effect set-up of Imbens and Angrist (1994), Abadie et al (2002), Abadie (2002Abadie ( , 2003, Frölich (2007) and Donald et al (2014aDonald et al ( , 2014b.…”
Section: Introductionmentioning
confidence: 99%
“…We impose this assumption for the sake of ease of discussion and note that our results could be easily extended to cases including discrete covariates and mediators, however, at the cost of more burdensome notation. That is, the sample would need to be stratified on the discrete values and SLE would have to be performed separately for each stratum, see Donald, Hsu, and Lieli (2014).…”
Section: Asymptotic Behaviourmentioning
confidence: 99%
“…When a causal effect is identified, a test of the unconfoundedness assumption may be devised by comparing the estimates of the causal effects obtained both under the unconfoundedness assumption and using the instrument (classical Durbin-WuHausman (DWH) test in a parametric setting). This was recently used by Donald et al [11] to propose a test of the unconfoundedness assumption in a nonparametric framework.…”
Section: Introductionmentioning
confidence: 99%
“…Indeed, to obtain the nonparametric identification of a local average causal effects stronger (and untestable) assumptions must be made on the instrument, see, e.g. Imbens and Angrist [12], Angrist et al [4], Angrist and Fernandez-Val [13], Donald et al [11] and Guo et al [14]. In particular, these papers use a monotonicity assumption saying that the instrument must affect the treatment in a monotone fashion, as well as do not allow for unobserved heterogeneity to affect both the instrument and the treatment.…”
Section: Introductionmentioning
confidence: 99%