Causal Analysis in Theory and Practice

Dear friends in causality research,

In the past 5 months, since the publication of The Book of Why http://bayes.cs.ucla.edu/WHY/ I have been involved in conversations with many inquisitive readers on Twitter @yudapearl and have not been able to update our blog as frequently as I should. I am glad to return to this forum and update it with the major developments since July, 2018.

1.
Initial reviews of the Book of Why are posted on its trailer page http://bayes.cs.ucla.edu/WHY/ They vary from technical discussions to philosophical speculations, from relationships to machine learning to debates about the supremacy of randomized contolled trials.

2.
A search-able file of all my 750 tweets is available here: https://ucla.in/2Kz0FoY. It can be used for (1) extracting talking points, adages and arguments in the defense of causal inference, and (2) understanding the thinking of neighboring cultures, e.g., statistics, epidemiology, economics, deep learning and reinforcement learning, primarily on issues of transparency, testability, manipulability, do-expressions and counterfactuals.

3.
The 6th printing of the Book Of Why is now available, with corrections to all errors and typos discovered up to Oct. 29, 2018. To check that you have the latest printing, make sure the last line on the copywright page ends with … 8 7 6

4.
Please examine the latest papers and reports from our brewry:

R-484 Pearl, “Causal and Counterfactual Inference,” Forthcoming section in The Handbook of Rationality, MIT press. https://ucla.in/2Iz9myt

R-484 Pearl, “A note on oxygen, matches and fires, On Non-manipulable Causes,” September 2018. https://ucla.in/2Qb1h6v

R-483 Pearl, “Does Obesity Shorten Life? Or is it the Soda? On Non-manipulable Causes,” https://ucla.in/2EpxcNU Journal of Causal Inference, 6(2), online, September 2018.

R-481 Pearl, “The Seven Tools of Causal Inference with Reflections on Machine Learning,” July 2018 https://ucla.in/2umzd65 Forthcoming, Communications of ACM.

R-479 Cinelli and Pearl, “On the utility of causal diagrams in modeling attrition: a practical example,” April 2018. https://ucla.in/2L8KAWw Forthcoming, Journal of Epidemiology.

R-478 Pearl and Bareinboim, “A note on `Generalizability of Study Results’,” April 2018. Forthcoming, Journal of Epidemiology. https://ucla.in/2NIsI6B

Earlier papers can be found here: http://bayes.cs.ucla.edu/csl_papers.html

5.
I wish in particular to call attention to the introduction of R-478, https://ucla.in/2NIsI6B. It provides a “three bullets” recipe for comparing
the structural and potential outcome frameworks:

* To determine if there exist sets of covariates $W$ that satisfy “conditional exchangeability”
** To estimate causal parameters at the target population in cases where such sets $W$ do not exist, and
*** To decide if one’s modeling assumptions are compatible with the available data.

I have listed the “three bullets” above in the hope that they serve to facilitate and concretize future conversations with our neighbors from the potential outcome framework.

6. We are informed of a most relevant workshop: AAAI-WHY 2019, March 26-27, Stanford, CA. The 2019 AAAI Spring Symposium will host a new workshop: Beyond Curve Fitting: Causation, Counterfactuals, and Imagination-based AI. See https://why19.causalai.net. Submissions due December 17, 2018

Greetings and Happy Holidays
Judea

Dear friends in causality research,

Three months ago, I sent you a special greeting, announcing the forthcoming publication of The Book of Why (Basic Books, co-authored with Dana MacKenzie). Below please find an update.

The Book came out on May 15, 2018, and has since been featured by the Wall Street Journal, Quanta Magazine, and The Times of London. You can view these articles here:
http://bayes.cs.ucla.edu/WHY/

Eager to allay public fears of the dangers of artificial intelligence, these three articles interpreted my critics of model-blind learning as general impediments to AI and machine learning. This has probably helped put the Book on Amazon’s #1 bestseller lists in several categories.

However, the limitations of current machine learning techniques are only part of the message conveyed in the Book of Why. The second, and more important part of the Book describes how these limitations are circumvented through the use of causal models, however qualitative or incomplete. The impacts that causal modeling has had on the social and health sciences make it only natural that a similar ‘revolution’ will soon be sweeping machine learning research, and liberate it from its current predicaments of opaqueness, forgetfulness and lack of explainability. (See, for example, http://www.sciencemag.org/news/2018/05/ai-researchers-allege-machine-learning-alchemy and https://arxiv.org/pdf/1801.00631.pdf)

I was happy therefore to see that this positive message was understood by many readers who wrote to me about the book, especially readers coming from traditional machine learning background (See, for example, www.inference.vc/untitled). It was also recognized by a more recent review in the New York Times
https://www.nytimes.com/2018/06/01/business/dealbook/review-the-book-of-why-examines-the-science-of-cause-and-effect.html which better reflects my optimism about what artificial intelligence can achieve.

I am hoping that you and your students will find inspiration in the optimistic message of the Book of Why, and that you take active part in the on-going development of “model-assisted machine learning.”

Sincerely,

Judea

Dear friends in causality research,

You may find an upcoming workshop at UAI to be of interest; see the details below for more information:

7th Causal Inference Workshop at UAI 2018 – Intercontinental, Monterey, CA; August 2018

Description
In recent years, causal inference has seen important advances, especially through a dramatic expansion in its theoretical and practical domains. By assuming a central role in decision making, causal inference has attracted interest from computer science, statistics, and machine learning, each field contributing a fresh and unique perspective.

More specifically, computer science has focused on the algorithmic understanding of causality, and general conditions under which causal structures may be inferred. Machine learning methods have focused on high-dimensional models and non-parametric methods, whereas more classical causal inference has been guiding policy in complex domains involving economics, social and health sciences, and business. Through such advances a powerful cross-pollination has emerged as a new set of methodologies promising to deliver robust data analysis than each field could individually — some examples include concepts such as doubly-robust methods, targeted learning, double machine learning, causal trees, all of which have recently been introduced.

This workshop is aimed at facilitating more interactions between researchers in machine learning, statistics, and computer science working on questions of causal inference. In particular, it is an opportunity to bring together highly technical individuals who are strongly motivated by the practical importance and real-world impact of their work. Cultivating such interactions will lead to the development of theory, methodology, and – most importantly – practical tools, that better target causal questions across different domains.

Important Dates
May 20 — Paper submission deadline; submission page: https://easychair.org/conferences/?conf=causaluai2018
June 20 — Author notification
July 20 — Camera ready version
August 10 — Workshop

Organizers
Bryant Chen, IBM
Panos Toulis, University of Chicago
Alexander Volfovsky, Duke University

Dear friends in causality research,

This greeting is somewhat different from those you have been receiving in the past 18 years (Yes, it has been that long, see http://causality.cs.ucla.edu/blog, January 1, 2000). Instead of new results, passionate discussions, breakthroughs, controversies, and question and answers sessions, this greeting brings you a musical offering: The Book of Why. It is a new book that I have co-authored recently with Dana MacKenzie (http://danamackenzie.com), forthcoming May 15, 2018. The book tells the story, in layman’s terms, of the new science of cause and effect, the one we have been nourishing, playing with, and marveling at on this blog.

By “the new science” I mean going back, not merely to the causal revolution of the past few decades, but all the way to the day when scientists first assigned a mathematical symbol to a causal relation.

Joining me in this journey you will see how leaders in your own field managed to cope with the painful transition from statistical to causal thinking.

Despite my personal obsession with mathematical tools, this book has taught me that the story of causal inference looks totally different from the conceptual, non-technical viewpoint of our intended readers. So different in fact that I occasionally catch myself tuning to the music of The Book of Why when seeking a deeper understanding of a dry equation. I hope you and your students find it as useful and as enjoyable.

The publisher’s description can be viewed here: http://bayes.cs.ucla.edu/WHY/why-book-coming-soon.pdf while the Table of Content and sample chapters can be viewed here: http://bayes.cs.ucla.edu/WHY/

Our publisher also assures us that the book can be pre-ordered at no extra cost, and on your favorite website.

And may our story be inscribed in the book of worthy causes.

Judea

Dear friends in causality research,

Welcome to the 2018 Winter Greeting from the UCLA Causality Blog. This greeting discusses the following topics:

1.  A report is posted, on the “What If” workshop at the NIPS conference  (see December 19, 2017 post below). It discusses my presentation of: Theoretical Impediments to Machine Learning, a newly revised version of which can be viewed here. [http://ftp.cs.ucla.edu/pub/stat_ser/r475.pdf]

2. New posting: “Facts and Fiction from the Missing Data Framework”. We are inviting discussion of two familiar mantras:
Mantra-1. “The role of missing data analysis in causal inference is well understood (eg causal inference theory based on counterfactuals relies on the missing data framework).
and
Mantra-2. “while missing data methods can form tools for causal inference, the converse cannot be true.”

We explain why we believe both mantras to be false, but we would like to hear you opinion before firming up our minds.

3. A review paper is available here:
http://ftp.cs.ucla.edu/pub/stat_ser/r473-L.pdf
Titled: “Graphical Models for Processing Missing Data.” It explains and demonstrates why missing data is a causal inference problem.

4. A new page is now up, providing information on “The Book of Why”
http://bayes.cs.ucla.edu/WHY/
It contains Table of Contents and excerpts from the book.

5. Nominations are now open for the ASA Causality in Education Award. The nomination deadline is March 1, 2018. For more information, please see
http://www.amstat.org/education/causalityprize/.

6. For those of us who were waiting patiently for the Korean translation of Primer — our long wait is finally over. The book is available now in colorful cover and in optimistic North Korean accent.
http://www.kyowoo.co.kr/02_sub/view.php?p_idx=1640&cate=0014_0017_

Don’t miss the gentlest introduction to causal inference.
http://bayes.cs.ucla.edu/PRIMER/

Enjoy, and have a productive 2018.
JP

Dear friends in causality research,

We would like to promote an upcoming causality workshop at UAI 2017. See the details below for more information:

Causality in Learning, Inference, and Decision-making: Causality shapes how we view, understand, and react to the world around us. It’s a key ingredient in building AI systems that are autonomous and can act efficiently in complex and uncertain environments. It’s also important to the process of scientific discovery since it underpins how explanations are constructed and the scientific method.

Not surprisingly, the tasks of learning and reasoning with causal-effect relationships have attracted great interest in the artificial intelligence and machine learning communities. This effort has led to a very general theoretical and algorithmic understanding of what causality means and under what conditions it can be inferred. These results have started to percolate through more applied fields that generate the bulk of the data currently available, ranging from genetics to medicine, from psychology to economics.

This one-day workshop will explore causal inference in a broad sense through a set of invited talks,  open problems sessions, presentations, and a poster session. In this workshop, we will focus on the foundational side of causality on the one hand, and challenges presented by practical applications on the other. By and large, we welcome contributions from all areas relating to the study of causality.

We encourage co-submission of (full) papers that have been submitted to the main UAI 2017 conference. This workshop is a sequel to a successful predecessor at UAI 2016.

Dates/Locations: August 15, 2017; Sydney, Australia.

Speakers: TBA

Registration and additional information: https://www.cs.purdue.edu/homes/eb/causal-uai17/

Hello friends in causality research!

UCLA is proud to host the 2017 West Coast Experiments Conference. See the details below for more information:

West Coast Experiments Conference: The WCE is an annual conference that brings together leading scholars and graduate students in economics, political science and other social sciences who share an interest in causal identification broadly speaking. Now in its tenth year, the WCE is a venue for methodological instruction and debate over design-based and observational methods for causal inference, both theory and applications.

Speakers: Judea Pearl, Rosa Matzkin, Niall Cardin, Angus Deaton, Chris Auld, Jeff Wooldridge, Ed Leamer, Karim Chalak, Rodrigo Pinto, Clark Glymour, Elias Barenboim, Adam Glynn, and Karthika Mohan.

Dates/Location: The tenth annual West Coast Experiments Conference will be held at UCLA on Monday, April 24 and Tuesday, April 25, 2017, preceded by in-depth methods training workshops on Sunday, April 23. Events will be held in the Covel Commons Grand Horizon Ballroom, 200 De Neve Drive, Los Angeles, CA 90095.

Fees: Attendance is free!

Registration and details: Space is limited; for a detailed schedule of events and registration, please visit: wce2017ucla.eventbrite.com

Greetings!

We would like to promote another causal inference short course. This 2-day seminar won the 2013 Causality in Statistics Education Award, given by the American Statistical Association. See the details below for more information:

Causal Inference with Directed Graphs: This seminar offers an applied introduction to directed acyclic graphs (DAGs) for causal inference. DAGs are a powerful new tool for understanding and resolving causal problems in empirical research. DAGs are useful for social and biomedical researchers, business and policy analysts who want to draw causal inferences from non-experimental data. The chief advantage of DAGs is that they are “algebra-free,” relying instead on intuitive yet rigorous graphical rules.

Instructor: Felix Elwert, Ph.D.

Who should attend: If you want to understand under what circumstances you can draw causal inferences from non-experimental data, this course is for you. Participants should have a good working knowledge of multiple regression and basic concepts of probability. Some prior exposure to causal inference (counterfactuals, propensity scores, instrumental variables analysis) will be helpful but is not essential.

Tuition: The fee of $995.00 includes all seminar materials.

Date/Location: The seminar meets Friday, April 28 and Saturday, April 29 at Temple University Center City, 1515 Market Street, Philadelphia, PA 19103.

Details and registration: http://statisticalhorizons.com/seminars/public-seminars/causal-inference-with-directed-graphs-spring

Greetings!

We’ve received news that Harvard is offering a short course on causal inference that may be of interest to readers of this blog. See the details below for more information:

An Introduction to Causal Inference: This 5-day course introduces concepts and methods for causal inference from observational data. Upon completion of the course, participants will be prepared to further explore the causal inference literature. Topics covered include the g-formula, inverse probability weighting of marginal structural models, g-estimation of structural nested models, causal mediation analysis, and methods to handle unmeasured confounding. The last day will end with a “capstone” open Q&A session.

Instructors: Miguel Hernán, Judith Lok, James Robins, Eric Tchetgen Tchetgen & Tyler VanderWeele

Prerequisites: Participants are expected to be familiar with basic concepts in epidemiology and biostatistics, including linear and logistic regression and survival analysis techniques.

Tuition: $450/person, to be paid at the time of registration. Tuition will be waived for up to 2 students with primary affiliation at an institution in a developing country.

Date/Location: June 12-16, 2017 at the Harvard T.H. Chan School of Public Health

Details and registration: https://www.hsph.harvard.edu/causal/shortcourse/

Dear friends in causality research,

In this brief greeting I would like to first call attention to an approaching deadline and then discuss a couple of recent articles.

1.
Causality in Education Award – March 1, 2017

We are informed that the deadline for submitting a nomination for the ASA Causality in Statistics Education Award is March 1, 2017. For purpose, criteria and other information please see http://www.amstat.org/education/causalityprize/ .

2.
The next issue of the Journal of Causal Inference (JCI) is schedule to appear March, 2017. See https://www.degruyter.com/view/j/jci

MY contribution to this issue includes a tutorial paper entitled: “A Linear ‘Microscope’ for Interventions and Counterfactuals”. An advance copy can be viewed here: http://ftp.cs.ucla.edu/pub/stat_ser/r459.pdf
Enjoy!

3.
Overturning Econometrics Education (or, do we need a “causal interpretation”?)

My attention was called to a recent paper by Josh Angrist and Jorn-Steffen Pischke titled: “Undergraduate econometrics instruction” (A NBER working paper) http://www.nber.org/papers/w23144?utm_campaign=ntw&utm_medium=email&utm_source=ntw

This paper advocates a pedagogical paradigm shift that has methodological ramifications beyond econometrics instruction; As I understand it, the shift stands contrary to the traditional teachings of causal inference, as defined by Sewall Wright (1920), Haavelmo (1943), Marschak (1950), Wold (1960), and other founding fathers of econometrics methodology.

In a nut shell, Angrist and Pischke  start with a set of favorite statistical routines such as IV, regression, differences-in-differences among others, and then search for “a set of control variables needed to insure that the regression-estimated effect of the variable of interest has a causal interpretation”. Traditional causal inference (including economics) teaches us that asking whether the output of a statistical routine “has a causal interpretation” is the wrong question to ask, for it misses the direction of the analysis. Instead, one should start with the target causal parameter itself, and asks whether it is ESTIMABLE (and if so how), be it by IV, regression, differences-in-differences, or perhaps by some new routine that is yet to be discovered and ordained by name. Clearly, no “causal interpretation” is needed for parameters that are intrinsically causal; for example, “causal effect”, “path coefficient”, “direct effect”, “effect of treatment on the treated”, or “probability of causation”.

In practical terms, the difference between the two paradigms is that estimability requires a substantive model while interpretability appears to be model-free. A model exposes its assumptions explicitly, while statistical routines give the deceptive impression that they run assumptions-free (hence their popular appeal). The former lends itself to judgmental and statistical tests, the latter escapes such scrutiny.

In conclusion, if an educator needs to choose between the “interpretability” and “estimability” paradigms, I would go for the latter. If traditional econometrics education
is tailored to support the estimability track, I do not believe a paradigm shift is warranted towards an “interpretation seeking” paradigm as the one proposed by Angrist and Pischke,

I would gladly open this blog for additional discussion on this topic.

I tried to post a comment on NBER (National Bureau of Economic Research), but was rejected for not being an approved “NBER family member”. If any of our readers is a “”NBER family member” feel free to post the above. Note: “NBER working papers are circulated for discussion and comment purposes.” (page 1).