## Date and Location

Feb 11, 2019 - 1:00pm to 2:00pm## Abstract

## Causal inference in statistics: An overview (final presentation by David Bernadett, continued from Feb 4)

Causal inference in statistics: An overview, J. Pearl, Statistics Surveys Vol. 3 (2009) 96–146

This review presents empirical researchers with recent advances in causal inference, and stresses the paradigmatic shifts that must be undertaken in moving from traditional statistical analysis to causal analysis of multivariate data. Special emphasis is placed on the assumptions that underly all causal inferences, the languages used in formulating those assumptions, the conditional nature of all causal and counterfactual claims, and the methods that have been developed for the assessment of such claims. These advances are illustrated using a general theory of causation based on the Structural Causal Model (SCM) described in Pearl (2000a), which subsumes and unifies other approaches to causation, and provides a coherent mathematical foundation for the analysis of causes and counterfactuals. In particular, the paper surveys the development of mathematical tools for inferring (from a combination of data and assumptions) answers to three types of causal queries: (1) queries about the effects of potential interventions, (also called “causal effects” or “policy evaluation”) (2) queries about probabilities of counterfactuals, (including assessment of “regret,” “attribution” or “causes of effects”) and (3) queries about direct and indirect effects (also known as “mediation”). Finally, the paper defines the formal and conceptual relationships between the structural and potential-outcome frameworks and presents tools for a symbiotic analysis that uses the strong features of both.

## Graphical Causal Models (presented by Vania Wang, Geography)

Cosma Rohilla Shalizi (2019) Graphical Causal Models. *Advanced Data Analysis from an Elementary Point of View*. (Chapter 21, pp 483 - 490).

Take a piece of cotton, say an old rag. Apply flame to it; the cotton burns. We say the fire caused the cotton to burn. The flame is certainly correlated with the cotton burning, but, as we all know, correlation is not causation. Perhaps every time we set rags on fire we handle them with heavy protective gloves; the gloves don’t make the cotton burn, but the statistical dependence is strong. So what is causation? We do not have to settle 2500 years (or more) of argument among philosophers and scientists. For our purposes, it’s enough to realize that the concept has a counter-factual component: if, contrary to fact, the flame had not been applied to the rag, then the rag would not have burned. On the other hand, the fire makes the cotton burn whether we are wearing protective gloves or not....

## Identifying Causal Effect from Observations (presented by Archana Rajendran, Computer Science)

Cosma Rohilla Shalizi (2019) Identifying Causal Effect from Observations. *Advanced Data Analysis from an Elementary Point of View*. (Chapter 22, pp 491 - 512).

Given the causal structure of a system, estimate the effects the variables have on each other....