(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)
I’ve successfully emptied my inbox:
And one result was to fill up the blog through mid-January.
I think I’ve been doing enough blogging recently, so my plan now is to stop for awhile and instead transfer my writing energy into articles and books. We’ll see how it goes.
Just to give you something to look forward to, below is a list of what’s in the queue. I’m sure I’ll be interpolating new posts on this and that—there is an election going on, after all, indeed I just inserted a politics-related post two days ago. And other things come up sometime that just can’t wait. Also, my co-bloggers are free to post on Stan or whatever else they want, whenever they want.
But this is what’s on deck so far:
In policing (and elsewhere), regional variation in behavior can be huge, and perhaps can give a clue about how to move forward.
Guy Fieri wants your help! For a TV show on statistical models for real estate
The p-value is a random variable
“What can recent replication failures tell us about the theoretical commitments of psychology?”
Documented forking paths in the Competitive Reaction Time Task
Shameless little bullies claim that published triathlon times don’t replicate
Boostrapping your posterior
You won’t be able to forget this one: Alleged data manipulation in NIH-funded Alzheimer’s study
Are stereotypes statistically accurate?
Will youths who swill Red Bull become adult cocaine addicts?
Science reporters are getting the picture
Modeling correlation of issue attitudes and partisanship within states
Tax Day: The Birthday Dog That Didn’t Bark
The history of characterizing groups of people by their averages
Calorie labeling reduces obesityObesity increased more slowly in California, Seattle, Portland (Oregon), and NYC, compared to some other places in the west coast and northeast that didn’t have calorie labelingWhat’s gonna happen in November?
An ethnographic study of the “open evidential culture” of research psychology
Things that sound good but aren’t quite right: Art and research edition
Michael Porter as new pincushion
Kaiser Fung on the ethics of data analysis
One more thing you don’t have to worry about
Evil collaboration between Medtronic and FDA
His varying slopes don’t seem to follow a normal distribution
A day in the life
Letters we never finished reading
Better to just not see the sausage get made
Oooh, it burns me up
Birthdays and heat waves
Publication bias occurs within as well as between projects
Graph too clever by half
Take that, Bruno Frey! Pharma company busts through Arrow’s theorem, sets new record!
A four-way conversation on weighting and regression for causal inference
How paracompact is that?
In Bayesian regression, it’s easy to account for measurement error
Garrison Keillor would be spinning etc
“Brief, decontextualized instances of colaughter”
The new quantitative journalism
It’s not about normality, it’s all about reality
Hokey mas, indeed
You may not be interested in peer review, but peer review is interested in you
Hypothesis Testing is a Bad Idea (my talk at Warwick, England, 2:30pm Thurs 15 Sept)
Genius is not enough: The sad story of Peter Hagelstein, living monument to the sunk-cost fallacy
Bayesian Statistics Then and Now
No guarantee
Let’s play Twister, let’s play Risk
“Evaluating Online Nonprobability Surveys”
Redemption
Pro Publica Surgeon Scorecard Update
Hey, PPNAS . . . this one is the fish that got away
FDA approval of generic drugs: The untold story
Acupuncture paradox update
More p-value confusion: No, a low p-value does not tell you that the probability of the null hypothesis is less than 1/2
Multicollinearity causing risk and uncertainty
Andrew Gelman is not the plagiarism police because there is no such thing as the plagiarism police.
Cracks in the thin blue line
Politics and chance
I refuse to blog about this one
“Find the best algorithm (program) for your dataset.”
NPR’s gonna NPR
Why the garden-of-forking-paths criticism of p-values is not like a famous Borscht Belt comedy bit
Don’t trust Rasmussen polls!
Astroturf “patient advocacy” group pushes to keep drug prices high
It’s not about the snobbery, it’s all about reality: At last, I finally understand hatred of “middlebrow”
The never-back-down syndrome and the fundamental attribution error
Michael Lacour vs John Bargh and Amy Cuddy
It’s ok to criticize
“The Prose Factory: Literary Life in England Since 1918” and “The Windsor Faction”
Note to journalists: If there’s no report you can read, there’s no study
Heimlich
No, I don’t think the Super Bowl is lowering birth weights
Gray graphs look pretty
Should you abandon that low-salt diet?
Transparency, replications, and publication
Is it fair to use Bayesian reasoning to convict someone of a crime?
“Marginally Significant Effects as Evidence for Hypotheses: Changing Attitudes Over Four Decades”
Some people are so easy to contact and some people aren’t.
Should Jonah Lehrer be a junior Gladwell? Does he have any other options?
Advice on setting up audio for your podcast
The Psychological Science stereotype paradox
We have a ways to go in communicating the replication crisis
Authors of AJPS paper find that the signs on their coefficients were reversed. But they don’t care: in their words, “None of our papers actually give a damn about whether it’s plus or minus.” All right, then!
Another failed replication of power pose
“How One Study Produced a Bunch of Untrue Headlines About Tattoos Strengthening Your Immune System”
Ptolemaic inference
How not to analyze noisy data: A case study
The problems are everywhere, once you know to look
“Generic and consistent confidence and credible regions”
Happiness of liberals and conservatives in different countries
Conflicts of interest
“It’s not reproducible if it only runs on your laptop”: Jon Zelner’s tips for a reproducible workflow in R and Stan
Unintentional parody of Psychological Science-style research redeemed by Dan Kahan insight
Rotten all the way through
Some modeling and computational ideas to look into
How to improve science reporting? Dan Vergano sez: It’s not about reality, it’s all about a salary
Kahan: “On the Sources of Ordinary Science Knowledge and Ignorance”
Why I prefer 50% to 95% intervals
How effective (or counterproductive) is universal child care? Part 1
How effective (or counterproductive) is universal child care? Part 2
“Another terrible plot”
Can a census-tract-level regression analysis untangle correlation between lead and crime?
The role of models and empirical work in political science
More on my paper with John Carlin on Type M and Type S errors
Should scientists be allowed to continue to play in the sandbox after they’ve pooped in it?
“Men with large testicles”
Sniffing tears perhaps not as effective as claimed
Thinking more seriously about the design of exploratory studies: A manifesto
From zero to Ted talk in 18 simple steps: Rolf Zwaan explains how to do it!
Individual and aggregate patterns in the Equality of Opportunity research project
Unfinished (so far) draft blog posts
Deep learning, model checking, AI, the no-homunculus principle, and the unitary nature of consciousness
How best to partition data into test and holdout samples?
Abraham Lincoln and confidence intervals
“Breakfast skipping, extreme commutes, and the sex composition at birth”
Discussion on overfitting in cluster analysis
Happiness formulas
OK, sometimes the concept of “false positive” makes sense.
“A bug in fMRI software could invalidate 15 years of brain research”
Interesting epi paper using Stan
How can you evaluate a research paper?
Some U.S. demographic data at zipcode level conveniently in R
So little information to evaluate effects of dietary choices
Frustration with published results that can’t be reproduced, and journals that don’t seem to care
Using Stan in an agent-based model: Simulation suggests that a market could be useful for building public consensus on climate change
Data 1, NPR 0
Dear Major Textbook Publisher
“So such markets were, and perhaps are, subject to bias from deep pocketed people who may be expressing preference more than actual expectation”
Temple Grandin
fMRI clusterf******
How to think about the p-value from a randomized test?
Avoiding selection bias by analyzing all possible forking paths
The social world is (in many ways) continuous but people’s mental models of the world are Boolean
Science journalist recommends going easy on Bigfoot, says you should bash of mammograms instead
Applying statistical thinking to the search for extraterrestrial intelligence
An efficiency argument for post-publication review
Bayes is better
What’s powdery and comes out of a metallic-green cardboard can?
Low correlation of predictions and outcomes is no evidence against hot hand
Jail for scientific fraud?
Is the dorsal anterior cingulate cortex “selective for pain”?
Quantifying uncertainty in identification assumptions—this is important!
If I had a long enough blog delay, I could just schedule this one for 1 Jan 2026
Historical critiques of psychology research methods
p=.03, it’s gotta be true!
Objects of the class “George Orwell”
Sorry, but no, you can’t learn causality by looking at the third moment of regression residuals
“The Pitfall of Experimenting on the Web: How Unattended Selective Attrition Leads to Surprising (Yet False) Research Conclusions”
Two unrelated topics in one post: (1) Teaching useful algebra classes, and (2) doing more careful psychological measurements
Transformative treatments
Comment of the year
Migration explaining observed changes in mortality rate in different geographic areas?
Fragility index is too fragile
When you add a predictor the model changes so it makes sense that the coefficients change too.
Nooooooo, just make it stop, please!
“Which curve fitting model should I use?”
We fiddle while Rome burns: p-value edition
The Lure of Luxury
Confirmation bias
Problems with randomized controlled trials (or any bounded statistical analysis) and thinking more seriously about story time
When do stories work, Process tracing, and Connections between qualitative and quantitative research
A small, underpowered treasure trove?
Problems with “incremental validity” or more generally in interpreting more than one regression coefficient at a time
No evidence of incumbency disadvantage?
To know the past, one must first know the future: The relevance of decision-based thinking to statistical analysis
Powerpose update
Absence of evidence is evidence of alcohol?
“Estimating trends in mortality for the bottom quartile, we found little evidence that survival probabilities declined dramatically.”
SETI: Modeling in the “cosmic haystack”
There should really be something here for everyone. I don’t remember half these posts myself, and I look forward to reading them when they come out!
P.S. It’s a good thing I blog for free because nobody could pay me enough for the effort that goes into it.
The post My next 170 blog posts (inbox zero and a change of pace) appeared first on Statistical Modeling, Causal Inference, and Social Science.
Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science
