Lightnews — Scholar-powered news

Reposted by Brian Boyle

Pavithra Suryanarayan @pavisuri.bsky.social · 3d

More than a decade of effort went into this magnificent dataset. What an incredible public good. People need to know how hard it is to do rigorous empirical work in political science.

Francesca R. Jensenius @fr-jensenius.bsky.social · 3d

Very happy to be able to share the polling-level dataset on Indian Parliamentary Elections 2009, 2014, 2019 that we have been working on for more than a decade. Both the data and the data descriptor are open access: rdcu.be/eujHH

@statsvitenskap.bsky.social @unioslo-svfak.bsky.social

Screen shot of the title and abstract of the article I am talking about

8 21

Reposted by Brian Boyle

Political Studies @polstudies.bsky.social · 5d

Do generous welfare policies foster political trust? Matthijs Gillissen, @silkegoubin.bsky.social & Anna Ruelens examine the long-term effects of welfare generosity on trust in political institutions. Read more:
buff.ly/rxgfboR

@polstudiesassoc.bsky.social @uoypolitics.bsky.social @sagepub.com

5 6

Reposted by Brian Boyle

Take Sipma @takesipma.bsky.social · 8d

Are universities perceived as left-wing bastions? Are police officers seen as right-wing? And are judges considered impartial?

In a new publication in @ejprjournal.bsky.social, Erika van Elsas, @mauritsmeijers.bsky.social, and I answer these questions ... (1/3)
www.cambridge.org/core/journal...

Citizen perceptions of ideological bias in public service institutions: A cross-institutional analysis in five countries | European Journal of Political Research | Cambridge Core

Citizen perceptions of ideological bias in public service institutions: A cross-institutional analysis in five countries

www.cambridge.org

3 18 35

Reposted by Brian Boyle

Joe Greenwood-Hau @niceonecombo.bsky.social · 8d

You can read the book and buy a copy with a 35% discount (using code 'Greenwood-Hau35') here:

liverpooluniversitypress.co.uk/doi/book/10....

Capital, Privilege and Political Participation | Home

This book will be available open access upon publication.

liverpooluniversitypress.co.uk

1 2

Reposted by Brian Boyle

Matthew Barnfield @mbarnfield.bsky.social · 9d

Following the success of our spring seminar series earlier this year, we @psapolpsychology.bsky.social are running an autumn/winter series, with four online presentations by great scholars.

Please do register and come along to hear about some really fascinating research!

PSA Political Psychology Specialist Group @psapolpsychology.bsky.social · 9d

This time in two weeks, we will launch our autumn/winter seminar series. We have an exciting line-up of four online talks covering a range of topics in political psychology.

All presentations are on Thursdays at 12:00 UK.

Sign up to attend here!: www.psa.ac.uk/specialist-g...

Political Psychology | The Political Studies Association (PSA)

Political Psychology is a multi-disciplinary group established to provide a forum for collaboration, discussion and support for political psychology scholars and practitioners as well as to facilitate...

www.psa.ac.uk

9 8

Brian Boyle @bpboyle.bsky.social · 10d

Our article about representation on BBC Question Time is now in print at IJPP. We find they closely reflected Brexit and Iraq war viewpoints of the public and MPs, but see a huge overrepresentation in guests from elite educational backgrounds @heinzbrandenburg.bsky.social @nclpolitics.bsky.social

Brian Boyle @bpboyle.bsky.social · Dec 17

Happy to share that our article (@heinzbrandenburg.bsky.social and Yulia Lemesheva) which looks at representation on BBC Question Time has now been published at IJPP journals.sagepub.com/doi/full/10....
@nclpolitics.bsky.social
@strathpolir.bsky.social

Sage Journals: Discover world-class research

Subscription and open access journals from Sage, the world's leading independent academic publisher.

journals.sagepub.com

6 9

Reposted by Brian Boyle

ryan cooper @ryanlcooper.com · 11d

"Plan for a future where you can buy GPUs for ten cents on the dollar, where there's a buyer's market for hiring skilled applied statisticians, and where there's a ton of extremely promising open source models" pluralistic.net/2025/09/27/e...

Pluralistic: The real (economic) AI apocalypse is nigh (27 Sep 2025) – Pluralistic: Daily links from Cory Doctorow

pluralistic.net

5 7 48

Reposted by Brian Boyle

Jack Bailey @jack-bailey.co.uk · 18d

🧵 The Gallagher index is the industry standard measure of disproportionality in political science 📈

What values do you think it can take? 📏

In my new paper, I show something surprising: under democratic conditions, it can never exceed 1 / √2 ≈ 0.707

4 5 17

Reposted by Brian Boyle

Vincent Arel-Bundock @vincentab.bsky.social · 24d

Whoa—my book is up for pre-order!

𝐌𝐨𝐝𝐞𝐥 𝐭𝐨 𝐌𝐞𝐚𝐧𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐭𝐨 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭 𝐒𝐭𝐚𝐭 & 𝐌𝐋 𝐌𝐨𝐝𝐞𝐥𝐬 𝐢𝐧 #Rstats 𝐚𝐧𝐝 #PyData

The book presents an ultra-simple and powerful workflow to make sense of ± any model you fit

The web version will stay free forever and my proceeds go to charity.

tinyurl.com/4fk56fc8

9 84 270

Reposted by Brian Boyle

Political Science Research and Methods @psrm.bsky.social · 23d

📊 Are populist attitudes evenly spread across the ideological spectrum?

➡️ Using CSES data from 43 countries, E Tamaki &
@drjungphd.bsky.social find a non-linear relationship: populism is strongest at the ideological extremes, forming a U-shape pattern www.cambridge.org/core/journal... #FirstView

2 12 25

Reposted by Brian Boyle

Lewis Tibbs @lewistibbs.bsky.social · 23d

Power and influence in Britain is still wielded by a slither of the population: the 7% who are privately educated and roughly 1% who go to Oxbridge for uni.

6 years after the last rendition of Elitist Britain, and the situation hasn’t really changed!

Huge privilege to be involved in this project.

The Sutton Trust @suttontrust.bsky.social · 23d

🚨 NEW: Britain’s most powerful people are still 5x more likely to have been privately educated than the general population.

Our brand-new research reveals that jobs in the media, business, charity, creative and public sectors remain dominated by those from private schools ⤵️🧵

1 3

Reposted by Brian Boyle

Bruno Rodrigues @brodriguesco.bsky.social · 24d

rixpress is now an @ropensci.org package!

Link: docs.ropensci.org/rixpress/

9 38

Reposted by Brian Boyle

Ceri Fowler @cerifowler.bsky.social · 25d

A reminder to submit your abstracts! We'd love your papers on gender + candidates, vote choices, turnout, the role of feminist + LGBT issues, gender gaps etc.!

Ceri Fowler @cerifowler.bsky.social · Sep 10

Delighted to say I'm chairing a section at ECPG 2026 with @jess-smith.bsky.social @rosieshorrocks.bsky.social @gefjonoff.bsky.social and @liranharsgor.bsky.social on Elections, Parties, and Voters! Please send your abstracts in - full info here: ecpr.eu/Events/Event... @ecprgender.bsky.social

1 3 5

Reposted by Brian Boyle

European Consortium for Political Research @ecpr.bsky.social · 25d

✨ How does 3 days of academic & social exchange in the beautiful city of Newcastle sound? #ecpg26

The European Conference on Politics and Gender @ecprgender.bsky.social is seeking Paper & Panel proposals to kickstart the event!

📆 15–17 Jun 2026
📍 @nclpolitics.bsky.social

⏳ 7 Nov buff.ly/1JuXxxz

Calling for Panels and Papers

European Consortium for Political Research

buff.ly

4 11

Reposted by Brian Boyle

Darren Dahly @statsepi.bsky.social · 26d

Thanks again to @avrilkennan.bsky.social for the opportunity to share some thoughts on research integrity and methodological rigor with a room full of Irish health research funders via @hrci.bsky.social. 🙏

youtu.be/5q8l-OV9Msc

1 5 21

Reposted by Brian Boyle

Ceri Fowler @cerifowler.bsky.social · Sep 10

Delighted to say I'm chairing a section at ECPG 2026 with @jess-smith.bsky.social @rosieshorrocks.bsky.social @gefjonoff.bsky.social and @liranharsgor.bsky.social on Elections, Parties, and Voters! Please send your abstracts in - full info here: ecpr.eu/Events/Event... @ecprgender.bsky.social

10 23

Reposted by Brian Boyle

Stuart Turnbull-Dugarte @turnbulldugarte.com · Sep 5

Radical right accommodation really does not work.

New paper out with this exceptionally talented team
@katharinalawall.bsky.social @robjohns75.bsky.social @drjennings.bsky.social @sarahobolt.bsky.social @zachdickson.bsky.social @danjdevine.bsky.social & @jack-bailey.co.uk

doi.org/10.31235/osf...

58 990 2.2K

Reposted by Brian Boyle

Richard Carr @richardcarr.bsky.social · Sep 4

“It’s your boy RC and here’s the top 8 reasons W.T. Cosgrave was downright skibidi in the face of some world class rizz coming out of our guy Eamon de Valera”

Glen O'Hara @gsoh31.bsky.social · Sep 4

University debacle latest: I actually laughed for ages when I read this. It's not good when people laugh at the institutions of the state in charge of regulating tens of billions of pounds.

1 2 3

Reposted by Brian Boyle

Daniel Villar @daniel-a-villar.bsky.social · Sep 4

Education will never be as engaging as entertainment, asking it to be is like asking veg to taste like fudge. That doesn’t change the fact that veg is good for you

Glen O'Hara @gsoh31.bsky.social · Sep 4

University debacle latest: I actually laughed for ages when I read this. It's not good when people laugh at the institutions of the state in charge of regulating tens of billions of pounds.

1 2

Reposted by Brian Boyle

The British Election Study @britishelectionstudy.com · Sep 3

Labour's strategy since the election seems designed to appeal to right-conservative voters.

This strategy hasn't worked on its own terms because they have lost the (very few) right-wing voters that they had, while also losing (much) larger numbers of left-wing voters.

Four graphs showing vote intention among 2024 Labour voters by immigration preferences (top-left), defence spending (top-right), taxation preferences (bottom-left), and welfare spending support (bottom-right). In short, each graph shows that Labour has lost a greater number of voters who support a 'left-liberal' position, while also losing the very few 'right-conservative' voters that they had at a higher rate.

13 130 320

Reposted by Brian Boyle

European Social Survey @ess-survey.bsky.social · Sep 2

New #research that included analysis of our democracy #data was recently published by Political Behavior (@springernature.com).

@chankaming.bsky.social (@newcastleuni.bsky.social 🇬🇧) explored whether authoritarians’ electoral success abroad can change citizens’ satisfaction with #democracy.

Can Authoritarians’ Electoral Success Abroad Change Citizens’ Satisfaction with Democracy? - Political Behavior

Authoritarians’ electoral victories often catch worldwide attention as they are detrimental to global democracy.

buff.ly

1 4 6

Brian Boyle @bpboyle.bsky.social · Sep 1

Congrats Kenn!

1 1

Reposted by Brian Boyle

𝙅𝙖𝙘🍩𝙗 𝙉𝙮𝙧𝙪𝙥 @jacobnyrup.bsky.social · Aug 27

We just released version 3.1 of WhoGov, a global dataset on members of government from 1966-2023. The update fixes the mistakes that came to our attention while creating the Paths to Power dataset + mistakes users have notified us of

More additions and updates to WhoGov are on their way, including:

Download dataset - Nuffield Politics Research Centre

A research note for version 3.1 of the dataset, the codebook, which describes the variables in the two datasets, and the online appendix are found here:

politicscentre.nuffield.ox.ac.uk

1 14 35

Reposted by Brian Boyle

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.

48 280 940

Reposted by Brian Boyle

Olivier Grisel @ogrisel.bsky.social · Aug 19

Today at #EuroScipy2025, @glemaitre58.bsky.social and I presented a tutorial on pitfalls of machine learning for imbalanced classification problems.

We discussed what (not) to do when fitting a classifier and obtaining degenerate precision or recall values.

probabl-ai.github.io/calibration-...

Imbalanced classification: pitfalls and solutions — Probabilistic calibration of cost-sensitive learning

probabl-ai.github.io

1 10 23