Testing for the Unconfoundedness Assumption Using an Instrumental Assumption

Luna, Xavier de; Johansson, Per

doi:10.1515/jci-2013-0011

Cited by 19 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Causal diagrams (see for example in Pearl, 1995) are often used in statistics, but have also gained popularity in economics (e.g., Chalak & White, 2011;White & Lu, 2011;Huber, 2013;de Luna & Johansson, 2014). They represent complex causal systems in an arguably more tractable way than a (long) system of equations for each of the random variables.…”

Section: Identification In Different Causal Modelsmentioning

confidence: 99%

A Cautionary Tale About Control Variables in IV Estimation

Deuchert

Huber

2017

Oxf Bull Econ Stat

View full text Add to dashboard Cite

Many instrumental variable (IV) regressions include control variables to justify(conditional) independence of the instrument and the potential outcomes. The plausibility of conditional IV independence crucially depends on the timing when the control variables are determined. This paper systemically works through different IV models and discusses the (conditions for the) satisfaction of conditional IV independence when controlling for covariates measured (a) prior to the instrument, (b) after the treatment, or (c) both. To illustrate these identification issues, we consider an empirical application using the Vietnam War draft risk as instrument either for veteran status or education to estimate the effects of these variables on labor market and health outcomes.

show abstract

Section: Identification In Different Causal Modelsmentioning

confidence: 99%

A Cautionary Tale About Control Variables in IV Estimation

Deuchert

Huber

2017

Oxf Bull Econ Stat

View full text Add to dashboard Cite

show abstract

“…When these alternatives are not feasible, researchers are advised to use sensitivity analysis (e.g., Cox, Kisbu-Sakarya, Miočević, & MacKinnon, 2013;Imai, Keele, & Yamamoto, 2010;Imai et al, 2011;Mauro, 1990) or significance tests to evaluate the unconfoundedness assumption (in econometrics, these are often referred to as tests of exogeneity; see, e.g., Blundell & Horowitz, 2007;Caetano, 2015;de Luna & Johansson, 2014;Donald, Hsu, & Lieli, 2014;Hausman, 1978). Although sensitivity analysis is useful to assess the robustness of the empirical conclusions drawn from a mediation model to potential confounding, in the present study we focus on significance tests to detect whether influential confounding is present in an estimated mediation model.…”

mentioning

confidence: 99%

“…Although sensitivity analysis is useful to assess the robustness of the empirical conclusions drawn from a mediation model to potential confounding, in the present study we focus on significance tests to detect whether influential confounding is present in an estimated mediation model. Common tests of unconfoundedness, again, require the availability of IVs (e.g., Blundell & Horowitz, 2007;de Luna & Johansson, 2014;Donald, Hsu, & Lieli, 2014;Hausman, 1978;Wooldridge, 2015). Caetano (2015) proposed a discontinuity test of exogeneity for a single predictor in a multivariate model that does not require an IV.…”

mentioning

confidence: 99%

Confounder detection in linear mediation models: Performance of kernel-based tests of independence

Wiedermann

2019

Behav Res

View full text Add to dashboard Cite

It is well-known that the identification of direct and indirect effects in mediation analysis requires strong unconfoundedness assumptions. Even when the predictor is under experimental control, unconfoundedness assumptions must be imposed on the mediator-outcome relation in order to guarantee valid indirect-effect identification. Researchers are therefore advised to test for unconfoundedness when estimating mediation effects. Significance tests to evaluate unconfoundedness usually rely on an instrumental variable (IV)-that is, a variable that is nonindependent of the explanatory variable and, at the same time, independent of all exogenous factors that affect the outcome when the explanatory variable is held constant. Because IVs may be hard to come by, the present study shows that confounders of the mediator-outcome relation can be detected without making use of IVs when variables are nonnormal. We show that kernel-based tests of independence are able to detect confounding under nonnormality. Results from a simulation study are presented that suggest that these tests perform well in terms of Type I error protection and statistical power, independent of the distribution or measurement level of the confounder. A real-world data example from the Job Search Intervention Study (JOBS II) illustrates how the presented approach can be used to minimize the risk of obtaining biased indirect-effect estimates. The data requirements and role of unconfoundedness tests as diagnostic tools are discussed. A Monte Carlo-based power analysis tool for sample size planning is also provided.

show abstract

“…Assumption 2 is also called "no unobserved confounding" (Robins, 1992). Unless additional experimental data are available or the data happen to contain a structure similar to an instrument (de Luna & Johansson, 2014;Entner, Hoyer, & Spirtes, 2013), it is untestable and therefore needs to be justified by subject-matter knowledge.…”

Section: Assumption 2 (Conditional Exchangeability)mentioning

confidence: 99%

Covariate selection strategies for causal inference: Classification and comparison

Witte

Didelez

2018

Biometrical J

View full text Add to dashboard Cite

When causal effects are to be estimated from observational data, we have to adjust for confounding. A central aim of covariate selection for causal inference is therefore to determine a set that is sufficient for confounding adjustment, but other aims such as efficiency or robustness can be important as well. In this paper, we review six general approaches to covariate selection that differ in the targeted type of adjustment set.We discuss and illustrate their advantages and disadvantages using causal diagrams. Moreover, the approaches and different ways of implementing them are compared empirically in an extensive simulation study. We conclude that there are considerable differences between the approaches but none of them is uniformly best, with performance depending on the chosen adjustment method as well as the true confounding structure. Any prior structural knowledge on the causal relations is helpful to choose the most appropriate method. K E Y W O R D Saverage causal effect, causal diagram, confounder selection, propensity score matching, variable selection 1270

show abstract

Testing for the Unconfoundedness Assumption Using an Instrumental Assumption

Cited by 19 publications

References 30 publications

A Cautionary Tale About Control Variables in IV Estimation

A Cautionary Tale About Control Variables in IV Estimation

Confounder detection in linear mediation models: Performance of kernel-based tests of independence

Covariate selection strategies for causal inference: Classification and comparison

Contact Info

Product

Resources

About