Counterfactuals

Causal Inference and the Data-fusion Problem

DSA ADS Course - 2021

Causal Inference, Data-fusion, Causal Analysis, Causal Data Science, Counterfactuals, Selection Bias

Discuss concepts and techniques of different approaches to causal analysis, the curse of big data, data fusion and bias challenges. Discuss biases such as: confounding, sampling selection, and cross-population biases, along with a general, potential mitigation nonparametric framework for handling biases.

Discuss appropriate use of counterfactuals in causal analysis and risk of reasonable inference vs. unreasonable inference.

Counterfactual Data-Fusion for Online Reinforcement Learners

DSA ADS Course - 2021

Causal Reinforcement Learning, Counterfactuals, Counterfactual Data-Fusion, Online Reinforcement Learners

Discuss counterfactuals, risks of data fusion, causal reinforcement learning and fusion of observational and experimental data.

Counterfactual Data-Fusion for Online Reinforcement Learners - June, 2017

Abstract

Suffcient Causes: On Oxygen, Matches, and Fires

DSA ADS Course - 2021

Suffcient Causes: On Oxygen, Matches, and Fires

Probability, Causality, Causal Inference, Counterfactuals, Suffcient Causes, Explanation, Abduction

2019

Abstract

We demonstrate how counterfactuals can be used to compute the probability that one event was/is a sufcient cause of another, and how counterfactuals emerge organically from basic scientifc knowledge, rather than manipulative experiments. We contrast this demonstration with the potential outcome framework and address the distinction between causes and enablers.

The Curse of Free-Will and the Paradox of Inevitable Regret

2013

Abstract

The paradox described below aims to clarify the principles by which empirical data are harnessed to guide decision making. It is motivated by the practical question of whether empirical assessments of the effect of treatment on the treated (ETT) can be useful for either policy evaluation or personal decisions.

Thinking About Causation: A Causal Language with Epistemic Operators

October, 2020

Abstract

This paper proposes a formal framework for modeling the interaction of causal and (qualitative) epistemic reasoning. To this purpose, we extend the notion of a causal model [16, 17, 26, 11] with a representation of the epistemic state of an agent. On the side of the object language, we add operators to express knowledge and the act of observing new information. We provide a sound and complete axiomatization of the logic, and discuss the relation of this framework to causal team semantics.

A Linear “Microscope” for Interventions and Counterfactuals

March, 2017

Abstract

This note illustrates, using simple examples, how causal questions of non-trivial character can be represented, analyzed and solved using linear analysis and path diagrams. By producing closed form solutions, linear analysis allows for swift assessment of how various features of the model impact the questions under investigation. We discuss conditions for identifying total and direct effects, representation and identification of counterfactual expressions, robustness to model misspecification, and generalization across populations.