Causal Analysis and Policy Assessment with Bayesian Networks and BayesiaLab

A Free 2-Hour Workshop on Causality for Policy Analysts and Researchers

Bayesian Network

The objective of this presentation is to provide a practical framework for causal effect estimation with non-experimental data. We will present a range of methods, including Directed Acyclic Graphs and Bayesian networks, which can help distinguish causation from association when working with data from observational studies.

The presentation revolves around a seemingly trivial example, Simpson’s Paradox, which turns out to be rather tricky to interpret in practice.

Beyond covering the theory of Directed Acyclic Graphs and Bayesian networks, we will show you an entire causal analysis workflow using the BayesiaLab software platform. If you are interested, you will be able to follow this exercise, during the workshop or afterwards, using a trial version of BayesiaLab (click here to download the BayesiaLab trial).

This workshop is a "live" version of a new 63-page BayesiaLab tutorial, Causality for Policy Assessment and 
Impact Analysis - Directed Acyclic Graphs and Bayesian Networks for Causal Identification and Estimation

Date and Location

January 13, 2015, 3:00pm-5:00pm

Meridien Business Center
11811 North Freeway
Suite 500
Houston, Texas 77060

Our venue is located just 15 minutes from the George Bush Intercontinental Airport (IAH).

Workshop Overview

What is Policy Analysis?

Causal Inference by Experiment

Causal Inference from Data plus Theory

Causal Effect Identification

Potential Outcomes Framework (Neyman-Rubin Model)
Using Directed Acyclic Graphs for Identification (e.g. Back-Door Criterion, etc.)

Simpson's Paradox

Computing the Effect Size Nonparametrically

Using Bayesian Networks and BayesiaLab for Effect Size Computation
Pearl's Graph Mutilation
Jouffe's Likelihood Matching

Managing Uncertainty Probabilistically with Bayesian Networks

Uncertain Evidence
Uncertainty about Policy Implementation (Probabilistic Intervention)
Using BayesiaLab for Optimization under Uncertainty

Who should attend? 

Policy analysts, decision makers, policy consultants, applied researchers, statisticians, social scientists, data scientists, ecologists, epidemiologists, econometricians, economists, market researchers, knowledge managers, students and teachers in related fields.

About the Presenter

Stefan ConradyStefan Conrady is the managing partner of Bayesia USA, the North American sales and marketing organization of France-based Bayesia S.A.S. 

Stefan studied Electrical Engineering in Ulm, Germany, and has extensive international management experience in the fields of product strategy, marketing, market research, and analytics, all with leading car brands, including Mercedes-Benz, BMW, Rolls-Royce, Nissan, and Infiniti. Most recently, prior to joining Bayesia, Stefan was heading the Analytics & Forecasting group at Nissan North America.

Throughout his assignments in North America, Europe, and Asia, Stefan gained first-hand experience of how Fortune 100 corporations perform impact assessments of strategic initiatives. Thus, he is in a unique position to speak about the real-world practice of policy analysis, which often ignores the important distinction between observational and causal inference.   

Free Registration

Location & Map

Meridien Business Center, 11811 North Freeway, Suite 500, Houston, Texas 77060

Please keep me posted about upcoming courses and events!