Benjamin Rosenbaum

The existence of the bariance implies the existence of the bean

Diese Kampagne braucht deine Unterstützung An die Bildungsministerkonferenz: Schluss mit dem Prekariat der Privatdozent:innen!

We ask all Privatdozent:innen, Professor:innen and other colleagues, including solidaric colleagues abroad, to sign this letter and thus support our cause. You can find and sign the letter via the following link: chng.it/VhcP5tDBBY

Alien Earth

A brief delve into the recent science history of network theory (including food webs)

They are calling it "The lemon of the north" on their website

Wünsche dem @verbrecherverlag.bsky.social alles Gute zum 30. Geburtstag. Aktuell auf meiner Leseliste ist der Sammelband "Klimawandel und Gesellschaftskritik"

MC Stan is here! Follow for the latest Stan news, and tag if you want us to repost your posts about new papers, packages, courses, etc. about Stan

Simulations are no longer just “nice to have.” They’re reshaping how we do statistics.

Care to learn more? Check out our paper arxiv.org/abs/2503.24011, accepted for publication in the upcoming theme issue of Philosophical Transactions A.

Poster for 90 minute workshop on HOW TO DESIGN BETTER EXPERIMENTS, by Mridul Thomas & Ravi Ranjan. Details: September 23rd 16:00 CEST ; 14:00 UTC Description: Experimental designs can make or break an experiment. A good experiment has a clear goal and efficiently uses experimental resources to achieve that goal. In this workshop, we will review what experiments are for, basic and advanced principles of designing experiments, and how to use simulations to evaluate designs before actually doing the experiment. We’ll do a moderate amount of coding in R and so experience with this would be helpful but is not required. We intend to have small-group discussions to help participants develop their own experiments, and encourage participants to think of a specific question they would like to answer with an experiment.

@raviranjan.bsky.social & I are teaching a free online workshop with on experimental design for environmental scientists on the 23rd.

We'll focus on using simulations to evaluate how well different experimental designs help achieve your goals.

Please sign up & share! forms.gle/MZTxeQs4UpMr...

Jetzt kommt es auf die Hochschulleitungen an
Nach dem Scheitern der Ampel muss die neue Koalition beim #Wissenschaftszeitvertragsgesetz endlich liefern. Gleichzeitig steigt der Druck auf die Rektorate und Präsidien.
Im Wiarda-Blog: www.jmwiarda.de/blog/2025/09...

Before becoming a computational ecologist, I was working in fluid dynamics (for airplanes). This is going to be an interesting and fun read!!

Release of CmdStan 2.37 We are very happy to announce that the 2.37.0 release of CmdStan is now available on Github! As usual, the release of CmdStan is accompanied by new releases of Stan Math, core Stan, and Stanc3. Thi…

Stan / CmdStan 2.37 release!
blog.mc-stan.org/2025/09/02/r...
- sum_to_zero_matrix type sums to zero across both rows and columns
- simplex and *_stochastic_matrix types should be now faster and more stable
- new functions exposing the built-in constraint implementations
1/2

Rare sighting of a theoretician in the field

2025 shit is hitting the fan so hard that Werner Herzog is starting social media

Davon mal abgesehen, dass der Begriff "Coach" kein rechtlich geschützter ist & jede/r sich so nennen kann (ich bitte auch alle Coaches in meiner Bubble, das Folgende nicht persönlich zu nehmen) – es braucht kein x-tes Coaching zu 'mental strength in academia', 'Wege aus Wissenschaft', 1/2

Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models).

Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve.

A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.

Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...

Google Scholar Is Doomed Academia built entire careers on a free Google service with zero guarantees. What could go wrong?

Since search is dead, how soon do you think Google Scholar is headed for the Google Graveyard? I'm betting it's soon, and academia is NOT prepared

We talk more about visual posterior predictive checking and above plots in teemusailynoja.github.io/visual-predi....

The next bayesplot release will give a warning if PPC bar graphs are used with less than 6 unique outcome values, with a link to a page containing suggestions for better plots. 4/4

A tuxedo cat about to drench himself in catnip

Brought out the good stuff for #caturday

It worked in the end with fighting a pen&paper index battle. But thanks for the hint, I'm quite new with nimble and didn't know this!

At least ChatGPT was good at telling me what does NOT work

Spent the better part of the morning trying to populate a non-square matrix in NIMBLE, with constants on upper triangle and variables on lower triangle and block. Extra-challenge: no if-statements and no custom running indices allowed, just slicing all the way. 🫠
#Rstats

staninside: Facilitating the Use of 'Stan' Within Packages Infrastructure and functions that can be used for integrating 'Stan' (Carpenter et al. (2017) &lt;<a href="https://doi.org/10.18637%2Fjss.v076.i01" target="_top">doi:10.18637/jss.v076.i01</a>&gt;) code into stand alone R packages which in turn use the 'CmdStan' engine which is often accessed through 'CmdStanR'. Details given in Stan Development Team (2025) &lt;<a href="https://mc-stan.org/cmdstanr/" target="_top">https://mc-stan.org/cmdstanr/</a>&gt;. Using 'CmdStanR' and pre-written 'Stan' code can make package installation easy. Using 'staninside' offers a way to cache user-compiled 'Stan' models in user-specified directories reducing the need to recompile the same model multiple times.

New on CRAN: staninside (0.0.4). View at https://CRAN.R-project.org/package=staninside

R packages LaplacesDemon or BayesianTools come to my mind

Sparsity information and regularization in the horseshoe and other shrinkage priors The horseshoe prior has proven to be a noteworthy alternative for sparse Bayesian estimation, but has previously suffered from two problems. First, there has been no systematic way of specifying a prior for the global shrinkage hyperparameter based on the prior information about the degree of sparsity in the parameter vector. Second, the horseshoe prior has the undesired property that there is no possibility of specifying separately information about sparsity and the amount of regularization for the largest coefficients, which can be problematic with weakly identified parameters, such as the logistic regression coefficients in the case of data separation. This paper proposes solutions to both of these problems. We introduce a concept of effective number of nonzero parameters, show an intuitive way of formulating the prior for the global hyperparameter based on the sparsity assumptions, and argue that the previous default choices are dubious based on their tendency to favor solutions with more unshrunk parameters than we typically expect a priori. Moreover, we introduce a generalization to the horseshoe prior, called the regularized horseshoe, that allows us to specify a minimum level of regularization to the largest values. We show that the new prior can be considered as the continuous counterpart of the spike-and-slab prior with a finite slab width, whereas the original horseshoe resembles the spike-and-slab with an infinitely wide slab. Numerical experiments on synthetic and real world data illustrate the benefit of both of these theoretical advances.

That's a good question. The method has a parameter controlling the level of sparsity and you can control it with a meaningful prior. Will have to read it up carefully before applying, it's described in the SI and refers to Piironen & Vehtari (2017)

Cool, they're also using the regularized horseshoe prior. I'm trying to estimate self-regulation in aquatic field data which seems to be notoriously hard, so I'll have to bring out the big guns, too

Cool, they're also using the regularized horseshoe prior. I'm trying to estimate self-regulation in aquatic field data which seems to be notoriously hard, so I'll have to bring out the big guns, too

Who would have thought: Sicherheit führt *nicht* zu #Einkuscheln. Existenzangst hingegen lähmt.
#PDprekär #IchBinHanna #IchBinReyhan #WissZeitVG

High response diversity and conspecific density‐dependence, not species interactions, drive dynamics of coral reef fish communities Species-to-species and species-to-environment interactions play a crucial role in community dynamics. However, disentangling these interactions in species-rich communities is challenging due to the ‘...

Paper recommendation: A sparse modelling approach for analyzing community dynamics (20-40 species), using a regularized horseshoe prior for N² species interactions (zero vs non-zero), and a dimension-reduction approach for the N² residual correlation matrix (influences of unmeasured covariates) 🔥