Instrument Validity Tests With Causal Forests

Farbmacher, Helmut; Guber, Raphael; Klaassen, Sven

doi:10.1080/07350015.2020.1847122

Cited by 7 publications

(6 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover for simulations of the IRM model, we make use of a DGP of Belloni, Chernozhukov, Fernández-Val, and Hansen (2017). The DGP for the IIVM is inspired by a simulation run in Farbmacher, Guber, and Klaassen (2020). We present the formal DGPs in the appendix.…”

Section: Inference On a Structural Parameter In Key Causal Modelsmentioning

confidence: 99%

DoubleML: An Object-Oriented Implementation of Double Machine Learning in R

Bach,

Kurz,

Chernozhukov

et al. 2024

J. Stat. Soft.

View full text Add to dashboard Cite

The R package DoubleML implements the double/debiased machine learning framework of Chernozhukov, Chetverikov, Demirer, Duflo, Hansen, Newey, and Robins (2018). It provides functionalities to estimate parameters in causal models based on machine learning methods. The double machine learning framework consists of three key ingredients: Neyman orthogonality, high-quality machine learning estimation and sample splitting. Estimation of nuisance components can be performed by various state-of-the-art machine learning methods that are available in the mlr3 ecosystem. DoubleML makes it possible to perform inference in a variety of causal models, including partially linear and interactive regression models and their extensions to instrumental variable estimation. The object-oriented implementation of DoubleML enables a high flexibility for the model specification and makes it easily extendable. This paper serves as an introduction to the double machine learning framework and the R package DoubleML. In reproducible code examples with simulated and real data sets, we demonstrate how DoubleML users can perform valid inference based on machine learning methods.

show abstract

Section: Inference On a Structural Parameter In Key Causal Modelsmentioning

confidence: 99%

DoubleML: An Object-Oriented Implementation of Double Machine Learning in R

Bach,

Kurz,

Chernozhukov

et al. 2024

J. Stat. Soft.

View full text Add to dashboard Cite

show abstract

“…Both methodologies can address endogeneity by leveraging instrumental variables. Integration of instrumental variables into the construction of the model is rather natural (Wang et al 2021); Stoffi et al (2020), and instrument validity tests are under development (Farbmacher et al, 2020). Estimation of regression DID models with instrumental variables (especially when there are interaction terms) can be a daunting task, compared to the causal forest models.…”

Section: Comparison Of Did Using Parametric Regression Andmentioning

confidence: 99%

“…2021); Stoffi et al. (2020), and instrument validity tests are under development (Farbmacher et al., 2020). Estimation of regression DID models with instrumental variables (especially when there are interaction terms) can be a daunting task, compared to the causal forest models.…”

Section: Problems Related To Health Intervention Programsmentioning

confidence: 99%

Business Analytics: Emerging Practice and Research Issues in the Health Insurance Industry

Terekhov

Demirezen

Aytuğ

2024

Production and Operations Management

View full text Add to dashboard Cite

This paper summarizes emerging practice and research issues in the health insurance industry. We provide an industry overview, epitomize business analytics applications, and outline current and emerging problems of interest to key stakeholders and researchers in information systems, operations management, and healthcare management. Specifically, we focus on three areas of research that are of importance to the health insurance industry as well as the healthcare system: (i) management and evaluation of intervention programs, (ii) creation of effective provider networks, and (iii) emerging issues such as the impact of a pandemic, patient communication and steering, and technological innovations in health care. We lay out brief details of how each of these problems can be formulated, where the data can be acquired (public and/or proprietary data sets), and provide guidance for solving them. For several of these problems, we provide models that span causal modeling, predictive modeling, and prescriptive modeling.

show abstract

“…The instrumental variable Z needs to satisfy three conditions to ensure that the IV model identifies a local average treatment effect (Farbmacher et al, 2020):…”

Section: Estimationmentioning

confidence: 99%

“…However, evaluating the validity and monotonicity conditions is not trivial, and suitable tests of these conditions have only recently been proposed in the econometric literature (Farbmacher et al, 2020;Huber and Mellace, 2014;Kitagawa, 2015;Mourifié and Wan, 2017).…”

Section: Validitymentioning

confidence: 99%

Care or self-care? The impact of informal care provision on health behaviour

Eibich

2021

View full text Add to dashboard Cite

show abstract

Instrument Validity Tests With Causal Forests

Cited by 7 publications

References 66 publications

DoubleML: An Object-Oriented Implementation of Double Machine Learning in R

DoubleML: An Object-Oriented Implementation of Double Machine Learning in R

Business Analytics: Emerging Practice and Research Issues in the Health Insurance Industry

Care or self-care? The impact of informal care provision on health behaviour

Contact Info

Product

Resources

About