Academic papers

Categories → Causal Inference

Causal Inference is developing fast and becoming more popular. The field is benefiting from the rapid development of new Machine Learning techniques.

Observational and Natural Experiments

We have included some review papers below which describe the use of Causal Inference in combination with Observational or Natural experiment designs, to help you understand how these concepts can be applied to your own work:

•  Martin, W. (2014). Making valid causal inferences from observational data. Preventive veterinary medicine, 113(3), 281-297.
• Gianicolo, E. A., Eichler, M., Muensterer, O., Strauch, K., & Blettner, M. (2020). Methods for evaluating causality in observational studies: Part 27 of a series on evaluation of scientific publications. Deutsches Ärzteblatt International, 117(7), 101.
• Hammerton, G., & Munafò, M. R. (2021). Causal inference with observational data: the need for triangulation of evidence. Psychological medicine, 51(4), 563-578.
• Raita, Y., Camargo Jr, C. A., Liang, L., & Hasegawa, K. (2021). Big data, data science, and causal inference: A primer for clinicians. Frontiers in Medicine, 8, 678047.

Causal Inference Fundamentals

There have been several key publications that have contributed to the development of modern causal inference, including the do-calculus and potential outcomes framework. Some of the most important ones are:

• Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of educational psychology, 66(5), 688-701. This paper introduced the potential outcomes framework, which is a way to conceptualize causal effects in terms of what would have happened under different treatment conditions.

• Holland, P. W. (1986). Statistics and causal inference. Journal of the American statistical Association, 81(396), 945-960. This paper introduced the concept of graphical models for causal inference and proposed the use of the do-calculus to calculate causal effects.

• Pearl, J. (1995). Causal diagrams for empirical research. Biometrika, 82(4), 669-710. This paper introduced the use of directed acyclic graphs (DAGs) to represent causal relationships and provided a systematic way of using the do-calculus to estimate causal effects.

• Pearl, J. (2000). Causality: models, reasoning, and inference. Cambridge university press. This book is a comprehensive treatment of causal inference, including the potential outcomes framework, graphical models, and the do-calculus, and provides a unified framework for understanding causality.

• Imbens, G. W., & Rubin, D. B. (2015). Causal inference in statistics, social, and biomedical sciences. Cambridge University Press. This book provides a comprehensive treatment of causal inference methods, including the potential outcomes framework and the use of randomized experiments and observational data. It has been cited over 10,000 times according to Google Scholar.

• Pearl, J. (2009). Causal inference in statistics: An overview. Statistics Surveys, 3, 96-146. This paper provides a broad overview of the potential outcomes framework, graphical models, and the do-calculus, as well as their applications in various fields. It has been cited over 4,000 times according to Google Scholar.

• Hernan, M. A., & Robins, J. M. (2020). Causal inference: What if. Boca Raton: Chapman & Hall/CRC. This book presents a modern approach to causal inference, building on the potential outcomes framework and the do-calculus, and providing practical guidance on how to use these tools in a variety of settings.

These publications have had a significant impact on the development of modern causal inference, providing a foundation for researchers to rigorously study causal relationships in a variety of fields.