What on earth are we modeling? Data or Reality? Reflections on structural equations, external validity, heterogeneity and missing data
Abstract
Recent developments in graphical models and the logic of counterfactuals have given rise to major advances in causal inference, including confounding control, policy analysis, misspecification tests, mediation, heterogeneity, selection bias, missing data and the integration of data from diverse studies. I attribute these developments to two methodological commitments that define the “deductive” or “model-based” approach”. First, a commitment to commence the analysis by asking what reality should be like for a solution to exist and, second, a commitment to encode reality in terms of data-generating processes, rather than distributions of observed or counterfactual variables. These two principles have led to a fruitful symbiosis between graphs and counterfactuals that has unified the potential outcome framework of Neyman, Rubin and Robins. with the SEM tradition of Wright, Duncan and Joreskog, and the econometric tradition of Haavelmo, Marschak and Heckman. Recent works further show that deductive causal analysis is helpful in meta-analysis and missing data applications, two problem areas previously thought to be the sole province of statistical analysis.
The talk will focus on the following questions:
1. What mathematics can tell us about “external validity” or
“generalizing across populations”
http://ftp.cs.ucla.edu/pub/stat_ser/r372.pdf
http://ftp.cs.ucla.edu/pub/stat_ser/r387.pdf
2. When and how can sample-selection bias be circumvented
http://ftp.cs.ucla.edu/pub/stat_ser/r381.pdf
http://ftp.cs.ucla.edu/pub/stat_ser/r405.pdf
3. What population data can tell us about
unsuspected heterogeneity.
http://ftp.cs.ucla.edu/pub/stat_ser/r406.pdf
4. What relationships are estimable from
partially missing data, and how.
http://ftp.cs.ucla.edu/pub/stat_ser/r406.pdf
Reference: J. Pearl, Causality (Cambridge University Press, 2000,
2009)
Working papers:
http://bayes.cs.ucla.edu/csl_papers.html
Judea Pearl is a professor of computer science and statistics at UCLA, and distinguished visiting professor at the Technion, Israel Institute of Technology. He has joined the faculty of UCLA in 1970, where he currently directs the Cognitive Systems Laboratory and conducts research in artificial intelligence, human reasoning and philosophy of science. Pearl has authored several hundreds research papers and three books: Heuristics (1984), Probabilistic Reasoning (1988), and Causality (2000;2009), He is a member of the National Academy of Engineering, the American Academy of Arts and Sciences, and a Fellow of the IEEE, AAAI and the Cognitive Science Society. Pearl received the 2008 Benjamin Franklin Medal for Computer and Cognitive Science and the 2011 David Rumelhart Prize from the Cognitive Science Society. In 2012, he received the Technion’s Harvey Prize and the ACM A.M. Turing Award. for the development of a calculus for probabilistic and causal reasoning.