Causal Analysis in Theory and Practice

December 20, 2014

A new book out, Morgan and Winship, 2nd Edition

Filed under: Announcement,Book (J Pearl),General,Opinion — judea @ 2:49 pm

Here is my book recommendation for the month:
Counterfactuals and Causal Inference: Methods and Principles for Social Research (Analytical Methods for Social Research) Paperback – November 17, 2014
by Stephen L. Morgan (Author), Christopher Winship (Author)
ISBN-13: 978-1107694163 ISBN-10: 1107694167 Edition: 2nd

My book-cover blurb reads:
“This improved edition of Morgan and Winship’s book elevates traditional social sciences, including economics, education and political science, from a hopeless flirtation with regression to a solid science of causal interpretation, based on two foundational pillars: counterfactuals and causal graphs. A must for anyone seeking an understanding of the modern tools of causal analysis, and a must for anyone expecting science to secure explanations, not merely descriptions.”

But Gary King puts it in a more compelling historical perspective:
“More has been learned about causal inference in the last few decades than the sum total of everything that had been learned about it in all prior recorded history. The first comprehensive survey of the modern causal inference literature was the first edition of Morgan and Winship. Now with the second edition of this successful book comes the most up-to-date treatment.” Gary King, Harvard University

King’s statement is worth repeating here to remind us that we are indeed participating in an unprecedented historical revolution:

“More has been learned about causal inference in the last few decades than the sum total of everything that had been learned about it in all prior recorded history.”

It is the same revolution that Miquel Porta noted to be transforming the discourse in Epidemiology (link).

Social science and Epidemiology have been spear-heading this revolution, but I don’t think other disciplines will sit idle for too long.

In a recent survey (here), I attributed the revolution to “a fruitful symbiosis between graphs and counterfactuals that has unified the potential outcome framework of Neyman, Rubin, and Robins with the econometric tradition of Haavelmo, Marschak, and Heckman. In this symbiosis, counterfactuals emerge as natural byproducts of structural equations and serve to formally articulate research questions of interest. Graphical models, on the other hand, are used to encode scientific assumptions in a qualitative (i.e. nonparametric) and transparent language and to identify the logical ramifications of these assumptions, in particular their testable implications.”

Other researchers may wish to explain the revolution in other ways; still, Morgan and Winship’s book is a perfect example of how the symbiosis can work when taken seriously.

October 29, 2014

Fall Greetings from UCLA Causality Blog

Filed under: Announcement,General — eb @ 6:10 am

Friends in causality research,
This Fall greeting from UCLA Causality blog contains:

A. News items concerning causality research,
B. New postings, new problems and new solutions.

A. News items concerning causality research
A1. The American Statistical Association has announced an early submission deadline for the 2015 “Causality in Statistics Education Award” — February 15, 2015.
For details and selection criteria, see http://www.amstat.org/education/causalityprize/

A2. Vol. 2 Issue 2 of the Journal of Causal Inference (JCI) is now out, and can be viewed here:
http://www.degruyter.com/view/j/jci.2014.2.issue-2/issue-files/jci.2014.2.issue-2.xml
As always, submissions are welcome on all aspects of causal analysis, especially those deemed methodological.

A3. New Tutorial: Causality for Policy Assessment and Impact Analysis, is offered by BayesiaLab , see here.

A4. A Conference on Counterfactual anaysis for Policy Evaluation will take place at USC, November 20, 2014
http://dornsife.usc.edu/conferences/cafe-conference-2014/

A5. A Conference focused on Causal Inference will take place at Kyoto, Japan, November 17-18, 2014
Kyoto International Conference on Modern Statistics in the 21st Century
General info: http://www.kakenhyoka.jp/conference/index_en.html
Program: http://www.kakenhyoka.jp/conference/file/program.pdf

B. New postings, new problems and new solutions.
B1. A confession of a graph-avoiding econometrician.

Guido Imbens explains why some economists do not find causal graphs to be helpful. Miquel Porta describes the impact of causal graphs in epidemiology as a “revolution”. The question naturally arises: “Are economists smarter than epidemiologists?” or, “What drives epidemiologists to seek the light of new tools while graph-avoiding economists resign to parial blindness?”

See [link] for attempted answer.

B2. Lord’s Paradox Revisited — (Oh Lord! Kumbaya!)

This is a historical journey which traces back Lord’s paradox from its original formulation (1967), resolves it using modern tools of causal analysis, explains why it presented difficulties in previous attempts at resolution and, finally, addresses the general issue of whether adjustments for pre-existing conditions is justified in group comparison applications.
Link: http://ftp.cs.ucla.edu/pub/stat_ser/r436.pdf

B3. “Causes of Effects and Effects of Causes”
http://ftp.cs.ucla.edu/pub/stat_ser/r431.pdf

An expansion of a previous note with same title, including additional demonstration that “causes of effects” are not metaphysical (Dawid, 2000) and a simple visualization of how the probability of necessity (PN) is shaped by experimental and observational findings. It comes together with “A note on Causes of Effects” link a rebuttal to recent attempts at mystification.

August 15, 2014

Video interview with Nick Jewell

Filed under: Announcement,Presentation — eb @ 1:30 am

Several readers had difficulty accessing my video interview with Professor Nicolas Jewell on “causality in statistics”.

I believe the following links should provide direct and smooth connection:
Part 1 of “Introduction to Causality” — interview with Nick Jewell, June 2014
Part 2 of “Introduction to Causality” — interview with Nick Jewell, June 2014

August 12, 2014

September Courses on Causal Inference and Bayesian Newtworks

Filed under: Announcement — moderator @ 7:00 pm

Coming up in September, BayesiaLab will conduct a conference and several courses at UCLA.

These include a 2-day Causal Inference Course (Sept. 19-20), a 3-Day introductory Bayesian Network Course (Sept. 16-18), and a BayesiaLab Users Conference (Sept. 23-24).

Details on program and registration can be obtained here:
http://www.bayesia.us/causal-inference-course
http://www.bayesia.us/2014-user-conference
Email: info@bayesia.us

August 1, 2014

Mid-Summer Greetings from UCLA Causality Blog

Filed under: Announcement,General — moderator @ 3:35 pm

Dear friends in causality research,

This greeting from UCLA Causality blog contains:
A. News items concerning causality research,
B. New postings, publications, slides and videos,
C. New scientific questions and some answers.

A. News items concerning causality research
A.1 The American Statistical Association has announced the 2014 winners of the “Causality in Statistics Education Award.” See http://www.amstat.org/newsroom/pressreleases/2014-CausalityinStatEdAward.pdf

Congratulations go to the honorees, Maya Peterson and Laura B. Balzer (UC Berkeley, biostatistics department), who will each receive a $5000 and a plaque at the 2014 Joint Statistical Meetings (JSM 2014) in Boston.

A.2 Vol. 2 Issue 2 of the Journal of Causal Inference (JCI) is scheduled to appear September, 2014. The TOC can be viewed here: http://degruyter.com/view/j/jci (click on READ CONTENT, under the cover picture)
As always, submissions are welcome on all aspects of causal analysis, especially those deemed heretical.

A.3 The 2014 World Congress on Epidemiology (IEA) will include a pre-conference program with two short courses dedicated to causal inference.
http://www.iea-course.org/index.php/pre-conference-course/program/program
IEA-2014, Anchorage , Alaska, August 16, 2014,

B. New postings, publications, slides and videos
B1. An interesting blog page dedicated to Sewall Wright’s 1921 paper “Correlation and causation” can be viewed here http://evaluatehelp.blogspot.com/2014/05/wright1st.html

It is intruiging to see how the first causal diagram came to the attention of the scientific community, in 1921. (It was immediately attacked, of course, by students of Karl Pearson.)

B.2 A video of my recent interview with professor Nick Jewell (UC Berkeley) concerning Causal Inference in Statistics, can now be watched by going to www.statisticsviews.com and clicking on the link next to the image.

B.3 A new review of Causality (Cambridge, 2009) has appeared in the Journal of Structural Equation Models, authored by Stephen West and Tobias Koch. See http://bayes.cs.ucla.edu/BOOK-2K/west-koch-review2014.pdf
My comments on this review will be posted here in a few days; stay tuned.

B.4 The paper “Trygve Haavelmo and the Emergence of Causal Calculus” is now available online on Econometric Theory, (10 June 2014), see here.

To the best of my knowledge, this is the first article on modern causal analysis that managed to penetrate the walls of mainstream econometric literature. Only time will tell whether this publication would help soften the enigmatic resistance of traditional economists to modern tools of causal analysis. Oddly, even those economists who have came to accept the structural reading of counterfactuals (e.g., Heckman and Pinto, 2013) still find it difficult to accept the second principle of causal inference: reading independencies from the model’s structure. See http://ftp.cs.ucla.edu/pub/stat_ser/r420.pdf

At any rate, the editors, Olav Bjerkholt and Peter Phillips, deserve a medal of courage for their heroic effort to create a dialogue between two civilizations.

B.5 To further facilitate this dialogue, Bryant Chen and I wrote a survey paper http://ftp.cs.ucla.edu/pub/stat_ser/r428.pdf which summarizes and illustrates the benefits of graphical tools in the context of linear models, where most economists feel secure and comfortable.

C. New scientific questions and some answers
There are new postings on our home page http://bayes.cs.ucla.edu/csl_papers.html that might earn your attention. Among them:

R-425 “Recovering from Selection Bias in Causal and Statistical Inference,” with E. Bareinboim and J. Tian,
We ask: Is there a general, non-parametric solution to the selection-bias problem posed by Berkson
and Heckman decades ago?
The answer is: Yes. The problem is illuminated, generalized and solved using graphical models — the language where knowledge resides.
(The article just received the Best Paper Award at the Annual Conference of the American Association for Artificial Intelligence (AAAI-2014), July 30, 2014.)
http://ftp.cs.ucla.edu/pub/stat_ser/r425.pdf

R-431. “Causes of effects and Effects of Causes”.
Question: Is it really the case that modern methods of causal analysis have neglected to deal with “causes of effects”, as claimed by a recent paper of Dawid, Fienberg and Faigman (2013)?.
Answer: Quite the contrary! See here:
http://ftp.cs.ucla.edu/pub/stat_ser/r431.pdf

R-428. “Testable Implications of Linear Structural Equation Models” with Bryant Chen and Jin Tian.
We ask: Is there a systematic way of unveiling the testable implications of a linear model with latent variables?
Answer: We provide an algorithm for doing so.
http://ftp.cs.ucla.edu/pub/stat_ser/r428.pdf

Finally, dont miss previous postings on our blog, for example:
1. On Simpson’s Paradox. Again?
2. Who Needs Causal Mediation?
3. On model-based vs. ad-hoc methods

Wishing you a productive summer,
Judea

April 30, 2014

2nd Cause-effect pairs challenge

Filed under: Announcement,Causal Effect — eb @ 12:10 am

We have received the following announcement from Isabelle Guyon, regarding the second contest on “cause-effect pairs”:

We launched a second edition of the cause-effect pairs challenge:

The ChaLearn Fast Causation Coefficient Challenge (ending June 15, 2014)
Link: https://www.codalab.org/competitions/1381

There are prizes and the winners will present their results at the Microsoft Faculty Summit in July 2014.

December 19, 2013

Winter-Greetings from the Causality Blog

Filed under: Announcement,General — eb @ 1:00 am

Dear friends in causality,

This greeting from UCLA Causality blog contains:
A. News items concerning causality research,
B. New postings, publications, slides and videos,
C. New questions and some answers.

1. Journal of Causal Inference – Vol. 1, Issue 2
The second issue of the Journal of Causal Inference is on its way, and an on-line posting date has been set for December 23 2013. The first issue, can be viewed here:
http://www.degruyter.com/view/j/jci.2013.1.issue-1/issue-files/jci.2013.1.issue-1.xml
or here:
http://www.degruyter.com/view/j/jci

As always, submissions are welcome on all aspects of causal analysis, especially those deemed heretical.

2. Causality book – new printing
The 3rd printing of Causality (2009, 2nd ed.) is finally out (as of Sept. 1), corrected and improved.

If you have an older printing and do not wish to buy another copy, all changes are marked in red here:
http://bayes.cs.ucla.edu/BOOK-09/causality2-errata-updated7_3_13.pdf

3. Special Issue on Counterfactuals
The latest issue of Cognitive Science is dedicated to counterfactual reasoning. Edited by Stephen Sloman, the Table of Content and on-line version are available here:
http://onlinelibrary.wiley.com/doi/10.1111/cogs.2013.37.issue-6/issuetoc

4. A Strange article in Science Magazine.
Two articles in Science Magazine and Nature were brought to our attention:
http://www.sciencemag.org/content/338/6106/496.abstract
http://www.nature.com/nphys/journal/v8/n12/full/nphys2497.html
The author claims that causal effects can be inferred from correlation, using an extended version of Granger Causality.
To me this sounds like squaring the circle; perhaps one of our readers can illuminate us.

5. Calls for papers on Causality
5.1 Isabell Guyon sent us a call for papers for Special Topic of JMLR on Causality and Experimental Design. See:
http://clopinet.com/isabelle/Projects/NIPS2013/Causality_Special_Topic_2014.html

5.2 The ACM TIST journal is planning a Special Issue on Causal Discovery and Inference, and has issued a call for papers.
See: http://tist.acm.org/CFPs/TIST-SI-CDI.html

6. Dennis Lindley, dead at 90
On a sad note, Dennis Lindley, a pioneer in Bayesian inference died last week, at age 90.
Lindley brought the “SEEING vs. DOING” distinction to the attention of the statistics community:
http://bayes.cs.ucla.edu/BOOK-2K/lindley-rev.pdf
He also adapted the causal interpretation of Simpson’s paradox ahead of his peers.
We will miss his intellect, curiosity and integrity.
A true gentleman.

7. New postings on this blog.
Since our last greetings, the following items were posted on this blog (you can view them below).
Aug. 9 , 2013, Larry Wasserman on JSM 2013
Oct. 26, 2013, Comments on Kenny’s Summary of Causal Mediation
Nov. 10, 2013, On Heckman and Pinto
Nov. 19, 2013, The Key to Understanding Mediation
Dec. 14 2013, “But where does the graph come from?”

8. New slides and videos available
* Slides of the tutorial on “Causes and Counterfactuals” preseted at NIPS-2013 (by Pearl and Bareinboim) are available here:
http://ftp.cs.ucla.edu/pub/stat_ser/nips-dec2013-pearl-bareinboim-tutorial.pdf
http://www.cs.ucla.edu/~eb/nips-dec2013-pearl-bareinboim-tutorial-full.pdf

* Video of an introductory lecture presented to economists (at Stanford) is available here:
http://gsb-mediasite.stanford.edu/mediasite/Play/4ee5b390c7ef456c9ba0b11d1a519d4b1d

9. New scientific questions and some answers
There are new postings on my home page
http://bayes.cs.ucla.edu/csl_papers.html
which might earn your attention. Among them:

420 – J. Pearl, “Reflections on Heckman and Pinto’s ‘Causal Analysis after Haavelmo”,
where I defend Haavelmo’s original theory of intervention against a Fisherian surrogate proposed in Heckman and Pinto (2013).
http://ftp.cs.ucla.edu/pub/stat_ser/r420.pdf

419 – Bareinboin, Lee, Honavar, Pearl “Transportability from Multiple Enironments with Limited Experiments”
where we ask (and answer) whether it is possible to combine experimental findings from many heterogeneous studies to get what we need.
http://ftp.cs.ucla.edu/pub/stat_ser/r419.pdf

417 – Pearl and Mohan “Recoverability and Testability of Missing Data.”
where we explain missing-data problems to the uninitiated using graphical models, and illustrate the concepts of recoverability and testability.
http://ftp.cs.ucla.edu/pub/stat_ser/r417.pdf

416 – J. Pearl “The Mathematics of Causal Inference”
A summary of a Lecture given at JSM-2013, which compiles the main mathematical results in causal inference.
http://ftp.cs.ucla.edu/pub/stat_ser/r416.pdf

414 – J. Pearl, “Understanding Simpson’s Paradox”
where I introduce a guessing game that exhibits perpetual reversals and argue that the paradox can safely be titled: “resolved”
http://ftp.cs.ucla.edu/pub/stat_ser/r414.pdf

410 – Mohan, Pearl and Tian “Graphical Models for Inference with Missing Data” (Newly Revised)
where we take a fresh look at missing data problems from a causal inference perspective and propose a new taxonomy for misssing data mechanisms.
http://ftp.cs.ucla.edu/pub/stat_ser/r410.pdf

363 – Pearl and Paz, “Confounding Equivalence in Causal Analysis” (Revised Oct 2013)
We ask: When would an adjustment for T introduce the same bias as an adjustment for Z, and we answer it by extending the results of the 2010 version of this paper.
http://ftp.cs.ucla.edu/pub/stat_ser/r343w.pdf

Wishing you a happy and productive new year,
Judea Pearl

November 10, 2013

Reflections on Heckman and Pinto’s “Causal Analysis After Haavelmo”

Filed under: Announcement,Counterfactual,Definition,do-calculus,General — moderator @ 4:50 am

A recent article by Heckman and Pinto (HP) (link: http://www.nber.org/papers/w19453.pdf) discusses the do-calculus as a formal operationalization of Haavelmo’s approach to policy intervention. HP replace the do-operator with an equivalent operator, called “fix,” which simulates a Fisherian experiment with randomized “do”. They advocate the use of “fix,” discover limitations in “do,” and inform readers that those limitations disappear in “the Haavelmo approach.”

I examine the logic of HP’s paper, its factual basis, and its impact on econometric research and education (link: http://ftp.cs.ucla.edu/pub/stat_ser/r420.pdf).

October 8, 2013

UCLA-Stats seminar: A Conversation on Statistical Methodology, with Judea Pearl

Filed under: Announcement,Discussion,General — eb @ 11:50 pm

UCLA Department of Statistics Seminar Series

Thu, 10/24/2013, 12:30 PM—1:30 PM
4660 Geology Bldg.

Judea Pearl and Joakim Ekstrom
Statistics
UCLA

A Conversation on Statistical Methodology, with Judea Pearl
http://statistics.ucla.edu/seminars/2013-10-24/12:30pm/4660-geology

Join us for a conversation on statistical methodology, and in particular the theory of causal inference. In this ‘Socratic dialogue’-styled conversation, recent A.M. Turing award winner Judea Pearl will discuss his views on statistical methodology with conversational partner Joakim Ekstrom. The conversation will start at R.A. Fisher’s randomization procedure for isolation of contributors to systematic variation, and then continue discussing the methodology of Judea Pearl for isolation and identification of causal factors in data obtained from sources other than perfectly randomized experiments.

In the conversation, there will be plenty of opportunity for attendees to ask questions, explore alternatives and raise objections, especially regarding ways of introducing causal inference in statistics education.

Judea Pearl is a Professor at UCLA Computer Science and Statistics, and has contributed greatly to the theory of causal inference. Joakim Ekstrom is a post-doctoral research scholar at UCLA Statistics, seminar co-organizer, and an expert on the theory and history of statistics.

September 23, 2013

CMU Workshop: Case Studies of Causal Discovery with Model Search

Filed under: Announcement,General — eb @ 1:50 am

We received the following announcement from Richard Scheines (Carnegie Mellon University):

CMU Workshop: Case Studies of Causal Discovery with Model Search, 

October 25-27, 2013, Pittsburgh, PA, USA.

Additional details can be found here: http://www.hss.cmu.edu/philosophy/casestudiesworkshop.php

« Previous PageNext Page »

Powered by WordPress