Lightnews — Scholar-powered news

Olaf Borghi @olafborghi.com · 28d

thank you for all the extremely helpful papers and blog posts!! so many of them are my go-to resources, and they came out surprisingly often with perfect timing for my work :)

2

Olaf Borghi @olafborghi.com · 28d

marginaleffects is one of my favourite R packages and this is such a great paper!! extremely recommended, alongside all other papers from the two authors and also the amazing and free Model to Meaning book marginaleffects.com

Julia M. Rohrer @dingdingpeng.the100.ci · Aug 25

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...

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.

1 4 23

Reposted by Olaf Borghi

Julia M. Rohrer @dingdingpeng.the100.ci · 29d

New paper out with @boryslaw.bsky.social 🥳 In which we sketch out how to rethink measurement invariance causally for applied researchers. And provide a causal definition of measurement invariance!

www.sciencedirect.com/science/arti...

Rethinking measurement invariance causally

Highlights:
It is preferable to work with a causal definition of measurement invariance
A violation of measurement invariance is a potentially substantively interesting observation
Standard tests for measurement invariance rely on strong assumptions
Group differences can be thought of as descriptive results

Conceptual graph illustration the central points of the manuscript. A group variable is potentiall connected to a construct of interest which affects items. Measurement invariance is violated if the group variable directly affects the items, for example by modifying the loadings from the construct to the items, or by directly affecting an item

To make this less abstract, consider a scenario where students take an exam, R, meant to capture some ability, T, and then are admitted to a program, V, depending on their exam results: R → V. This is sufficient to result in a violation of the statistical definition of measurement invariance. Exam results and admission are not independent given ability because exam results have a direct effect on admission. Even if we know somebody’s ability (e.g., we know it’s very high), learning about their admission status (e.g., they were not admitted) can tell us something about their exam result (e.g., it may have been worse than expected). According to the causal definition, this in itself does not constitute measurement bias, which seems a sensible conclusion here. After all, the scenario does not involve any reason to believe that the measurement process varied systematically by admission status. Admission happens after the exams took place, it cannot retroactively influence the measurement process (and, for example, lead to unfair treatment depending on admission status).

3 36 110

Olaf Borghi @olafborghi.com · Jul 22

This is incredible work, such an insanely cool paper and findings! Quite alarming that "[post-training and prompting methods that] increased AI persuasiveness [...] also systematically decreased factual accuracy"

Kobi Hackenburg @kobihackenburg.bsky.social · Jul 21

Today (w/ @ox.ac.uk @stanford @MIT @LSE) we’re sharing the results of the largest AI persuasion experiments to date: 76k participants, 19  LLMs, 707 political issues.

We examine “levers” of AI persuasion: model scale, post-training, prompting, personalization, & more!

🧵:

1

Reposted by Olaf Borghi

Mariana von Mohr @marianavonmohr.bsky.social · Jul 17

In previous work with Manos Tsakiris @mtsakiris.bsky.social , we showed that interoception can act as a buffer against political stress. We now extend this research to the 2024 U.S. Presidential elections, capturing data before and after

Check out our preprint 👇

osf.io/preprints/ps...

OSF

osf.io

3 12

Reposted by Olaf Borghi

Leonardo Carella @leonardocarella.bsky.social · Jul 9

I'm glad someone did basic due diligence on the wolf paper. (Although - worth noting - PNAS has an impact factor of 9 and Electoral Studies an impact factor of 2: a familiar pattern with replications of fundamentally flawed findings.) www.sciencedirect.com/science/arti...

The East in wolf’s clothing. Wolf attacks correlate with but do not cause far-right voting

The resurgence of wolves in Germany has sparked intense debate, particularly in rural areas where wolf attacks on livestock are frequent. Prior resear…

www.sciencedirect.com

5 23

Reposted by Olaf Borghi

Mariana von Mohr @marianavonmohr.bsky.social · Jul 8

Sharing our work at #ISPP in beautiful Prague on affective prescription —and how this shapes the kind of political leader we’re drawn to based on their appearance.
Preprint coming soon!

1 4

Olaf Borghi @olafborghi.com · Jul 4

This book is highly recommended! Bonus is that I genuinely enjoyed working through it when it first came out

Mike Frank @mcxfrank.bsky.social · Jul 1

Experimentology is out today!!! A group of us wrote a free online textbook for experimental methods, available at experimentology.io - the idea was to integrate open science into all aspects of the experimental workflow from planning to design, analysis, and writing.

Experimentology cover: title and curves for distributions.

1 6

Reposted by Olaf Borghi

Mariana von Mohr @marianavonmohr.bsky.social · Jul 3

Great talk by @olafborghi.com on cognitive control and politically motivated reasoning, even in the face of unexpected interference 👇😂 #ISPP2025

1 4

Reposted by Olaf Borghi

Olaf Borghi @olafborghi.com · Jul 2

(1/6) #ISPP2025 is just one day away and I can't wait to be in Prague! It will be the first conference I attend during my PhD - looking forward to all the interesting sessions, catching up with friends, and meeting new people! 🤩 #PsychSciSky #polisky #CogSci #polpsy

1 1 4

Reposted by Olaf Borghi

Lisa DeBruine @debruine.bsky.social · Jul 2

As one of my favourite colleagues Etienne Roesch just whispered to me in response to a #MetaScience2025 speaker suggesting AI could act as an additional grant reviewer:

A👏I👏is👏not👏an👏analytic👏tool

1 2 12

Reposted by Olaf Borghi

Manos Tsakiris @mtsakiris.bsky.social · Jul 1

That’s the correct link :
www.jobs.london.ac.uk/Job/JobDetai...

8 1

Olaf Borghi @olafborghi.com · Jul 2

(6/6) You can find a curated collection of our contributions to ISPP 2025 here: docs.google.com/document/d/1...

IPPAD_ISPP2025

ISPP 2025 Annual Meeting in Prague IP-PAD Program Interdisciplinary Perspectives on the Politics of Adolescence & Democracy Conference days Thursday, 3rd of July 3 10:15-11:30 Gustavo Cout...

docs.google.com

Olaf Borghi @olafborghi.com · Jul 2

(5/6) If you are looking for more interdisciplinary talks bridging cognitive and political sciences and young people's politics, also check out the 15+(!!) contributions from my colleagues from the ippad.eu network, including three full panels

politics & adolescence | ippad

IP-PAD (Interdisciplinary Perspectives on the Politics of Adolescence & Democracy) is a Doctoral Network that aims to address a timely, pressing societal issue, namely the understanding of how the dev...

ippad.eu

1 1

Olaf Borghi @olafborghi.com · Jul 2

(4/6) It will feature four talks on the involvement of young people in politics, a highly policy-relevant area given the discussions on lowering the voting age where political psychology can make an important contribution! With interdisciplinary discussants @mtsakiris.bsky.social and Kaat Smets

2

Olaf Borghi @olafborghi.com · Jul 2

(3/6) Together with amazing collaborators from ippad.eu, I also co-organised Session 127: Young People's Political Agency and Voting Rights - Sunday 8:30 AM. I know, a bit early for the last day of the conference, but I promise that getting out of bed early will be worth it!

politics & adolescence | ippad

IP-PAD (Interdisciplinary Perspectives on the Politics of Adolescence & Democracy) is a Doctoral Network that aims to address a timely, pressing societal issue, namely the understanding of how the dev...

ippad.eu

1

Olaf Borghi @olafborghi.com · Jul 2

(2/6) I'll be presenting and chairing Session 19: Biological and Psychometric Approaches on Thursday 10:15 AM. Come by if you want to hear about my recent preprint on politically motivated reasoning and its cognitive correlates, and more exciting interdisciplinary research! doi.org/10.31234/osf...

OSF

doi.org

1 1

Olaf Borghi @olafborghi.com · Jul 2

(1/6) #ISPP2025 is just one day away and I can't wait to be in Prague! It will be the first conference I attend during my PhD - looking forward to all the interesting sessions, catching up with friends, and meeting new people! 🤩 #PsychSciSky #polisky #CogSci #polpsy

1 1 4

Reposted by Olaf Borghi

Julia M. Rohrer @dingdingpeng.the100.ci · Jun 18

To re-up this, this also applies to latent growth curve models 😭 😭 😭
No, I'm afraid you cannot solve a fundamental identification problem by applying a latent growth curve model.

Julia M. Rohrer @dingdingpeng.the100.ci · May 27

PSA: Don’t trust anyone who tells you that you can identify age or period or cohort effects simply by applying the right statistical model to the right type of data. This is fundamentally misunderstanding the nature of the age-period-cohort problem!>

Arrested Development meme.

People have suggested empirically solving the APC problem just by applying the right model to the right data

Well did it work for those people

Not, it never does, I mean, these people somehow delude themselves into thinking it might, but...

...but it might work for us.

3 3 35

Reposted by Olaf Borghi

Dr Lucy Foulkes @lucyfoulkes.bsky.social · May 21

I’m in the Guardian today, arguing that we should stop them all-class mental health lessons in schools

I've thought very carefully about ‘going public’ with this, because it's a sensitive argument to make, especially in the face of so many young people struggling.

(cont 🧵)

tinyurl.com/vun92cz7

Mental-health lessons in schools sound like a great idea. The trouble is, they don’t work | Lucy Foulkes

All-class therapy sessions don’t help, and may even make matters worse. The evidence shows we need different solutions, says Dr Lucy Foulkes, an academic psychologist at Oxford University

www.theguardian.com

12 95 190

Reposted by Olaf Borghi

Dr Lucy Foulkes @lucyfoulkes.bsky.social · Apr 25

This is a *key* new paper in the world of school mental health interventions

A very large trial (N=6388) testing a universal CBT-based app for adolescent depression (13-14y)

No effects found (on depression, anxiety, distress or insomnia)

(🧵)

mentalhealth.bmj.com/content/28/1...

Future Proofing Study: a cluster randomised
controlled trial evaluating the effectiveness of a
universal school-based cognitive–behavioural
programme for adolescent depression

13 94 230

Reposted by Olaf Borghi

SCAN Unit @scanunit.bsky.social · Apr 16

🚨 Come work with us!

3-year fully funded PhD position in Social and Cognitive Neuroscience @univie.ac.at @clauslamm.bsky.social to join our project investigating prosocial behavior under uncertainty.

More info: shorturl.at/1fnb2

Please share widely 🔁

3y_PhDposition_univie_ScanUnit.pdf

shorturl.at

1 38 29

Reposted by Olaf Borghi

Alex Coppock @aecoppock.bsky.social · Apr 16

New visualization tool alert!

The vayr package version 1.0.0 is now on CRAN.

It contains position adjustments for ggplot2 that help with overplotting in pleasing ways. My favorite is position_sunflower().

- install.packages("vayr")
- alexandercoppock.com/vayr

#rstats #ggplot2 #dataviz

3 55 200

Reposted by Olaf Borghi

Julia M. Rohrer @dingdingpeng.the100.ci · Apr 12

Proudly presenting the (for now) final version of "Why experiments work." To share the materials in a slightly more professional manner, I added a "Resources" page to my website: juliarohrer.com/resources/.

That was long overdue anyway; now there's also a curated list of my papers and blog posts.

6 46 190

Reposted by Olaf Borghi

Boryana Todorova @todorova.bsky.social · Apr 9

🧠🌍 Thrilled to share our latest paper, just out in Current Opinion in Behavioral Sciences:
"Neuroscience and climate action: intersecting pathways for brain and planetary health"
Read here (OA!): www.sciencedirect.com/science/arti...

1/

1 4 26