Author: Andrew

“Bayesian Meta-Analysis with Weakly Informative Prior Distributions”

Donny Williams sends along this paper, with Philippe Rast and Paul-Christian Bürkner, and writes: This paper is similar to the Chung et al. avoiding boundary estimates papers (here and here), but we use fully Bayesian methods, and specifically the half-Cauchy prior. We show it has as good of performance as a fully informed prior based […]

The post “Bayesian Meta-Analysis with Weakly Informative Prior Distributions” appeared first on Statistical Modeling, Causal Inference, and Social Science.

The persistence of bad reporting and the reluctance of people to criticize it

Mark Palko pointed to a bit of puff-piece journalism on the tech entrepreneur Elon Musk that was so extreme that it read as a possible parody, and I wrote, “it could just be as simple as that [author Neil] Strauss decided that a pure puff piece would give him access to write a future Musk […]

The post The persistence of bad reporting and the reluctance of people to criticize it appeared first on Statistical Modeling, Causal Inference, and Social Science.

Should the points in this scatterplot be binned?

Someone writes: Care to comment on this paper‘s Figure 4? I found it a bit misleading to do scatter plots after averaging over multiple individuals. Most scatter plots could be “improved” this way to make things look much cleaner than they are. People are already advertising the paper using this figure. The article, Genetic analysis […]

The post Should the points in this scatterplot be binned? appeared first on Statistical Modeling, Causal Inference, and Social Science.

He wants to model a proportion given some predictors that sum to 1

Joël Gombin writes: I’m wondering what your take would be on the following problem. I’d like to model a proportion (e.g., the share of the vote for a given party at some territorial level) in function of some compositional data (e.g., the sociodemographic makeup of the voting population), and this, in a multilevel fashion (allowing […]

The post He wants to model a proportion given some predictors that sum to 1 appeared first on Statistical Modeling, Causal Inference, and Social Science.

Joint inference or modular inference? Pierre Jacob, Lawrence Murray, Chris Holmes, Christian Robert discuss conditions on the strength and weaknesses of these choices

Pierre Jacob, Lawrence Murray, Chris Holmes, Christian Robert write: In modern applications, statisticians are faced with integrating heterogeneous data modalities relevant for an inference, prediction, or decision problem. In such circumstances, it is convenient to use a graphical model to represent the statistical dependencies, via a set of connected “modules”, each relating to a specific […]

The post Joint inference or modular inference? Pierre Jacob, Lawrence Murray, Chris Holmes, Christian Robert discuss conditions on the strength and weaknesses of these choices appeared first on Statistical Modeling, Causal Inference, and Social Science.

Divisibility in statistics: Where is it needed?

The basics of Bayesian inference is p(parameters|data) proportional to p(parameters)*p(data|parameters). And, for predictions, p(predictions|data) = integral_parameters p(predictions|parameters,data)*p(parameters|data). In these expressions (and the corresponding simpler versions for maximum likelihood), “parameters” and “data” are unitary objects. Yes, it can be helpful to think of the parameter objects as being a list or vector of individual parameters; and […]

The post Divisibility in statistics: Where is it needed? appeared first on Statistical Modeling, Causal Inference, and Social Science.

I think they use witchcraft

The following came in the email today: On Jul 7, 2018, at 12:58 PM, Submissions <submissions@**.co.in> wrote: Hello Dr. Andrew Gelman, I am Dr. ** [American-sounding name], Research Assistant for the ** Publishing Company contacting you with reference from our Editorial Board. Are you tired of publishing your Manuscript in useless journals and get no […]

The post I think they use witchcraft appeared first on Statistical Modeling, Causal Inference, and Social Science.

He wants to know what to read and what software to learn, to increase his ability to think about quantitative methods in social science

A law student writes: I aspire to become a quantitatively equipped/focused legal academic. Despite majoring in economics at college, I feel insufficiently confident in my statistical literacy. Given your publicly available work on learning basic statistical programming, I thought I would reach out to you and ask for advice on understanding modeling and causal inference […]

The post He wants to know what to read and what software to learn, to increase his ability to think about quantitative methods in social science appeared first on Statistical Modeling, Causal Inference, and Social Science.

All of Life is 6 to 5 Against

Donny Williams writes: I have a question I have been considering asking you for a while. The more I have learned about Bayesian methods, including regularly reading the journal Bayesian Analysis (preparing a submission here, actually!), etc., I have come to not only see that frequency properties are studied of Bayesian models, but it is […]

The post All of Life is 6 to 5 Against appeared first on Statistical Modeling, Causal Inference, and Social Science.

Tutorial: The practical application of complicated statistical methods to fill up the scientific literature with confusing and irrelevant analyses

James Coyne pointed me with distress or annoyance to this new paper, “Tutorial: The Practical Application of Longitudinal Structural Equation Mediation Models in Clinical Trials,” by K. A. Goldsmith, D. P. MacKinnon, T. Chalder, P. D. White, M. Sharpe, and A. Pickles. This is the team behind the PACE trial for systemic exercise intolerance disease. […]

The post Tutorial: The practical application of complicated statistical methods to fill up the scientific literature with confusing and irrelevant analyses appeared first on Statistical Modeling, Causal Inference, and Social Science.

On this 4th of July, let’s declare independence from “95%”

Plan your experiment, gather your data, do your inference for all effects and interactions of interest. When all is said and done, accept some level of uncertainty in your conclusions: you might not be 97.5% sure that the treatment effect is positive, but that’s fine. For one thing, decisions need to be made. You were […]

The post On this 4th of July, let’s declare independence from “95%” appeared first on Statistical Modeling, Causal Inference, and Social Science.

PNAS forgets basic principles of game theory, thus dooming thousands of Bothans to the fate of Alderaan

Under the subject line, “I needed this information to make a go/no-go decision on my new Death Star,” Kevin Lewis points to this press release from a prestigious journal: Because versions of the below articles were previously posted online, PNAS is publishing the articles without embargo: Potential atmospheres around TRAPPIST-1 planets Simulations of stellar winds […]

The post PNAS forgets basic principles of game theory, thus dooming thousands of Bothans to the fate of Alderaan appeared first on Statistical Modeling, Causal Inference, and Social Science.

About that claim in the NYT that the immigration issue helped Hillary Clinton? The numbers don’t seem to add up.

Today I noticed an op-ed by two political scientists, Howard Lavine and Wendy Rahm, entitled, “What if Trump’s Nativism Actually Hurts Him?”: Contrary to received wisdom, however, the immigration issue did not play to Mr. Trump’s advantage nearly as much as commonly believed. According to our analysis of national survey data from the American National […]

The post About that claim in the NYT that the immigration issue <em>helped</em> Hillary Clinton? The numbers don’t seem to add up. appeared first on Statistical Modeling, Causal Inference, and Social Science.

Flaws in stupid horrible algorithm revealed because it made numerical predictions

Kaiser Fung points to this news article by David Jackson and Gary Marx: The Illinois Department of Children and Family Services is ending a high-profile program that used computer data mining to identify children at risk for serious injury or death after the agency’s top official called the technology unreliable. . . . Two Florida […]

The post Flaws in stupid horrible algorithm revealed because it made numerical predictions appeared first on Statistical Modeling, Causal Inference, and Social Science.

The Ponzi threshold and the Armstrong principle

Mark Palko writes of the Ponzi threshold: “sometimes overhyped companies that start out with viable business plans see their valuation become so inflated that, in order to meet and sustain investor expectations, they have to come up with new and increasingly fantastic longshot schemes, anything that sounds like it might possibly pay off with lottery […]

The post The Ponzi threshold and the Armstrong principle appeared first on Statistical Modeling, Causal Inference, and Social Science.

Does “status threat” explain the 2016 presidential vote? Diana Mutz replies to criticism.

A couple months ago we reported on an article by sociologist Steve Morgan, criticizing a published paper by political scientist Diana Mutz. Mutz’s original article was called, “Status Threat, Not Economic Hardship, Explains the 2016 Presidential Vote,” and Morgan’s reply is called, “Status Threat, Material Interests, and the 2016 Presidential Vote” (it originally had the […]

The post Does “status threat” explain the 2016 presidential vote? Diana Mutz replies to criticism. appeared first on Statistical Modeling, Causal Inference, and Social Science.

On deck through the rest of the year

July: The Ponzi threshold and the Armstrong principle Flaws in stupid horrible algorithm revealed because it made numerical predictions PNAS forgets basic principles of game theory, thus dooming thousands of Bothans to the fate of Alderaan Tutorial: The practical application of complicated statistical methods to fill up the scientific literature with confusing and irrelevant analyses […]

The post On deck through the rest of the year appeared first on Statistical Modeling, Causal Inference, and Social Science.

Anyone want to run this Bayesian computing conference in 2022?

OK, people think I’m obsessive with a blog with a 6-month lag, but that’s nothing compared to some statistics conferences. Mylène Bédard sends this along for anyone who might be interested: The Bayesian Computation Section of ISBA is soliciting proposals to host its flagship conference: Bayes Comp 2022 The expectation is that the meeting will […]

The post Anyone want to run this Bayesian computing conference in 2022? appeared first on Statistical Modeling, Causal Inference, and Social Science.