Skip to primary content

Statistical Modeling, Causal Inference, and Social Science

Search

Main menu

Home
Authors
Blogs We Read
Sponsors

Post navigation

Multiple imputation and multilevel analysis Some interesting unpublished ideas on survey weighting

Bringing Causal Models Into the Mainstream

Posted on May 10, 2011 12:16 PM by Andrew

John Johnson writes at the Statistics Forum.

This entry was posted in Causal Inference by Andrew. Bookmark the permalink.

Art
Bayesian Statistics
Causal Inference
Decision Theory
Economics
Jobs
Literature
Miscellaneous Science
Miscellaneous Statistics
Multilevel Modeling
Papers
Political Science
Public Health
Sociology
Sports
Stan
Statistical computing
Statistical graphics
Teaching
Zombies

Fafa on More discussion of differential privacy at the CensusMay 17, 2022 9:41 PM
I appreciate Jessica replying here, but the comments are a great example of DP defenders goalpost moving and obfuscation. Point…
judea pearl on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 9:34 PM
All, I have summarized the above in a blog entry titled: "What statisticians mean by `Causal Inference': Is Gelman's blog…
Daniel Lakeland on I had big plans for that four-fifths of a penny: False precision and fraudMay 17, 2022 5:44 PM
For accounting it's a bad idea but for financial calculations like modeling stuff to decide what's the best investment strategy…
Jessica Hullman on More discussion of differential privacy at the CensusMay 17, 2022 5:36 PM
On 1, there is definitely an element of trust in the Census Bureau that is required given that they have…
Steve on I had big plans for that four-fifths of a penny: False precision and fraudMay 17, 2022 5:23 PM
"You should NOT do floating point calculationg with money."
Steve on I had big plans for that four-fifths of a penny: False precision and fraudMay 17, 2022 5:22 PM
Hasn't anyone seen Office Space? You should do floating point calculations with money. Bad things happen.
Christian Hennig on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 4:58 PM
@Josh: I may be misunderstood as saying that statistics should be left to highly trained experts (it may not be…
Robert Kern on I had big plans for that four-fifths of a penny: False precision and fraudMay 17, 2022 4:26 PM
I think that's right. The complaint is describing the alleged actions which involved changing the raw entries (which themselves were…
Nick on I had big plans for that four-fifths of a penny: False precision and fraudMay 17, 2022 4:16 PM
Indeed, from a quick reading of the court document, it seems that the absurd number of digits of "precision" were…
anon e mouse on More discussion of differential privacy at the CensusMay 17, 2022 3:28 PM
I think there are two main things that demographers are upset about (as well as many minor things): 1) The…
Keith O'Rourke on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 3:18 PM
Hennig quote "The fact that P-values (and statistical reasoning in general) regard idealised models that are different from reality seems…
Hans on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 2:34 PM
Thank you! You say that it is possible to estimate individual causal effects using causal inference if you have appropriate…
Anonymous on Do celebrated scientists have the free will to admit they are wrong? Not always!May 17, 2022 2:09 PM
There is, however, an argument for admitting the mistake: eventually her grant funding could dry up if people perceive her…
Keith O'Rourke on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 1:21 PM
C. Hennig quote "The fact that P-values (and statistical reasoning in general) regard idealised models that are different from reality…
Keith O'Rourke on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 1:19 PM
Josh: You wont know how difficult it is to explain the role that models play until you try and if…
Jessica Hullman on More discussion of differential privacy at the CensusMay 17, 2022 12:45 PM
It's fair to say that questions like how many 18 year olds shouldn't be called bizarre. To call me a…
Josh Rushton on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 12:44 PM
That makes sense, and is a good warning for me that my impulse to separate "fundamental ideas" from "implementation details"…
psyoskeptic on Do celebrated scientists have the free will to admit they are wrong? Not always!May 17, 2022 12:39 PM
Oops... posted before finishing. Anyway, I argued that she had quite a few motivations to maintain and defend her position,…
pysoskeptic on Do celebrated scientists have the free will to admit they are wrong? Not always!May 17, 2022 12:30 PM
Certainly there are degrees of agency. I look at a researcher like Ellen Bialystock who was facing a couple of…
Fafa on More discussion of differential privacy at the CensusMay 17, 2022 11:28 AM
The DP extremism is bizarre. I don't understand the attraction. To say "noisy counts" should be "normalized", is a ridiculous…
Jonathan (another one) on Do celebrated scientists have the free will to admit they are wrong? Not always!May 17, 2022 11:23 AM
I think I tried not to reply and failed. Or did I try? Or did I fail? Or am I…
Dale Lehman on How should journals handle submissions of non-reproducible research?May 17, 2022 10:17 AM
I want to push back on your claim that "a lot of the work during the pandemic" used data that…
David Pascall on How should journals handle submissions of non-reproducible research?May 17, 2022 9:43 AM
Some research that can't be reproduced due to legal or commercial reasons is clearly valuable. A lot of the work…
Anonymous on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 9:28 AM
Yes, this is excellent.
Robert R. Tucci on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 8:30 AM
Okay, Andrew, but let me clarify that what I meant by "missing information" is the missing information in a counterfactual…
Andrew on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 7:40 AM
Robert: No, I'm not saying that causal inference and prediction are different! I think of causal inference as a special…
Christian Hennig on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 7:04 AM
This is an interesting point. I believe though that what is hard is more than just technical details; even more…
Andrew on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 7:03 AM
Judea: I agree that the phrase "causal inference" is used in different ways by different people. That is the point…
Robert R. Tucci on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 6:02 AM
Andrew says: >>But the term “causal inference” in statistics and econometrics typically seems to be reserved for black-box setting. >>Once…
judea pearl on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 17, 2022 5:10 AM
Re-reading your post, I pause at every line that mentions "causal inference" and I say to myself: This is not…
Josh Rushton on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 17, 2022 2:06 AM
I should have brushed up my history on Wikipedia before I posted. The core idea I was talking about was…
ojm on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 10:45 PM
Here's a short summary of some thoughts: https://www.researchgate.net/profile/Oliver-Maclaren/publication/353841613_Models_identifiability_and_estimability_in_causal_inference/links/6114fbf51e95fe241ac6a157/Models-identifiability-and-estimability-in-causal-inference.pdf Longer thoughts: https://arxiv.org/abs/1904.02826
Josh Rushton on “A much bigger problem is the tension between the difficulty of statistics and the demand for it to be simple and readily available.”May 16, 2022 10:43 PM
This discussion might benefit from a clearer (louder?) separation of statistical *methods* from statistical *thinking*. Whenever I hear someone trashing…
Jessica Hullman on More discussion of differential privacy at the CensusMay 16, 2022 10:34 PM
Yeah, I guess there are many stories one could tell oneself about what sort of dynamics *might* arise. The survey…
Z on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 9:39 PM
I think Noah is saying that in the fertilizer example even after modeling fertilizer spread you still need to do…
rsm on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 8:54 PM
《When a good becomes more expensive, people buy less of it》 How do you explain the stock market?
Morris on More discussion of differential privacy at the CensusMay 16, 2022 7:21 PM
test
Andrew on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 6:02 PM
Judea: I did not state that you need a mechanistic model to get individual effects.
Andrew on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 6:00 PM
Judea: See P.S. above. I do consider mechanistic models (for example, for dosing in pharmacology) to be causal. And I'm…
judea pearl on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 5:57 PM
Individual effects are well captured within the framework of causal inference, because every SCM (structural causal model) can be regarded…
judea Pearl on “Causal” is like “error term”: it’s what we say when we’re not trying to model the process.May 16, 2022 5:39 PM
A rare, half-way agreement with Andrew who wrote: "statisticians use the term “causal inference” when we’re not trying to model…
Andrew on More discussion of differential privacy at the CensusMay 16, 2022 5:19 PM
Jessica/Priyanka: Interesting discussion. You're bringing in a third concern, so it's now privacy, accuracy, and trust. Once you have opened…
rsm on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 3:24 PM
If Guantanamo offered torture tours, would they make more than bullfights?
Dale Lehman on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 2:23 PM
Sure, anyone should be able to blog about well-being, even economists. But the idea that I "should" buy things rather…
Peter Dorman on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 2:10 PM
I didn't mean to imply that economists or political scientists (or statisticians or whoever) have no business blogging about well-being!…
Steve on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 2:05 PM
+1000 It is amazing that people can believe they are measuring a quantity about individuals by looking at aggregate behaviour…
Andrew on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 1:56 PM
Peter: I don't think of Tabarrok, or me, as having any particular insights regarding well-being. What Tabarrok offers, and what…
Peter Dorman on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 1:40 PM
For many years I was preoccupied with tweaks to utility theory -- behavioral econ stuff and strategies to restore true…
Phil on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 1:13 PM
"Goods vs experiences" has been discussed for decades, perhaps centuries (or millennia!), by hoi polloi and by academics; not just…
gec on Buying things vs. buying experiences (vs. buying nothing at all): Again, we see a stock-versus-flow confusionMay 16, 2022 12:50 PM
> The advocates of the new minimalism are, by and large, urban dwellers Is this true? I am not nor…

Proudly powered by WordPress