Lightnews — Scholar-powered news

Reposted by Martin Naunov

Alexander Wuttke @kunkakom.bsky.social · 29d

All of us—including myself—should publish fewer but better papers.
And we should spend more of our time on scrutinizing existing work, so we know which claims can be trusted. But that's hard work with little recognition.
Thanks @sophieehill.bsky.social for doing it. Impressive 🕵️‍♀️ work. Fun to read.

Sophie E. Hill @sophieehill.bsky.social · Sep 8

Blog post: github.com/sophieehill/...

TL;DR: There are a LOT of errors/inconsistencies in the results reported in this paper (estimates outside CIs, sign errors, duplicates, asymmetric CIs). Even in the abstract itself!

This suggests manual editing of results tables.

Which is not good...

🧵

Summary
Unfortunately, this example is not an isolated issue.

Across 9 appendix tables with 256 regression coefficients, I find:

5 cases of estimates outside their reported confidence interval
46 duplicates (i.e. estimate/CI combinations with an identical match in the same table)
At least 20 cases of asymmetric confidence intervals, which cannot be explained as rounding errors
17 values rounded to 4 decimal places (all others to 3 decimal places), indicating manual editing of tables
Over 50% of all estimates and confidence intervals are multiples of 0.008
It is difficult to diagnose exactly what is going on without access to the underlying data and code.

However, two broad conclusions can be drawn:

There are many errors and inconsistencies in the results which appear to be the result of manual editing.
There are strange patterns in the results which, if genuine, should have been noted and explained by the authors.

2 7 17

Reposted by Martin Naunov

Peter Luca Versteegen @versteegenluca.bsky.social · Aug 26

When people hear others’ views on politically sensitive topics (e.g., migration, abortion), they quickly become disrespectful or disengage. How can we express our views in such a way that they foster respect and interaction?

@emilykubin.bsky.social, @kurtjgray.bsky.social & I studied this.
🧵1/7

1 10 21

Martin Naunov @naunovmartin.bsky.social · Jun 3

Thanks so much for the shout-out, Luca! :)

1

Martin Naunov @naunovmartin.bsky.social · Jun 2

Thanks so much for the shout-out, Laura! 🙏

1

Martin Naunov @naunovmartin.bsky.social · Jun 1

Happy Pride! Let’s keep pushing for the kind of inclusion & egalitarianism that doesn’t demand we “cover” or tone down our (minoritized) identities & blend into the mainstream 🌈

4

Martin Naunov @naunovmartin.bsky.social · Jun 1

It’s #PrideMonth 🌈 & I'm proud to share my new JOP article. Using a survey experiment, I show: Republicans still penalize gay candidates. Democrats do not—but they do penalize even subtle gender nonconformity, expecting gay cands to look & sound “straight”
www.journals.uchicago.edu/doi/10.1086/...

The Right Kind of (Gay) Man? Sexuality, Gender Presentation, and Heteronormative Constraints on Electability | The Journal of Politics: Vol 0, No ja

www.journals.uchicago.edu

1 5 21

Martin Naunov @naunovmartin.bsky.social · May 23

Thank you thank you! I remember chatting with you about this project over coffee mid-May 2021. Feels so good it’s finally out! 🙂

Reposted by Martin Naunov

mark brandt @mjbsp.bsky.social · May 20

New lab preprint, from @abbycassario.bsky.social's furiously typing fingers to your eyes

PsyArXivBot @psyarxivbot.bsky.social · May 20

Does Threat Cause Increases in Conservatism? Evidence from Three Large Experiments in the United States Says No: https://osf.io/eqznx

1 10 20

Martin Naunov @naunovmartin.bsky.social · May 19

Love this! Congrats again on the awesome article and on the well-deserved spotlight!

Reposted by Martin Naunov

Stuart Turnbull-Dugarte @turnbulldugarte.com · May 19

A Tinder Test of Democratic Norms💋

New paper in @thejop.bsky.social with @bertous.bsky.social

We rely on a visual conjoint experiment, cross-sectional data, & panel data to show that affective polarization drives the normalisation of the far right among the centre-right 🇬🇧🇪🇸
doi.org/10.1086/736698

10 120 280

Martin Naunov @naunovmartin.bsky.social · May 17

Thank you, Drew!! Hope we can catch up soon :)

Martin Naunov @naunovmartin.bsky.social · May 17

Thanks so much!!

1

Martin Naunov @naunovmartin.bsky.social · May 17

Thank you!

Martin Naunov @naunovmartin.bsky.social · May 16

Thanks for the shout-out, friend!!

Martin Naunov @naunovmartin.bsky.social · May 16

Thank you, Andrew! And yes—would love that. We should def make a point of celebrating these wins together :)

Martin Naunov @naunovmartin.bsky.social · May 16

Thank you, Matt!!

Martin Naunov @naunovmartin.bsky.social · May 16

Thanks so much!! That means a lot!

2

Martin Naunov @naunovmartin.bsky.social · May 16

Thanks for the shout-out — and for all your support—friend! ♥️

1

Martin Naunov @naunovmartin.bsky.social · May 16

11 / If the manuscript is gated for you, let me know—I’m happy to share a copy via e-mail.

4

Martin Naunov @naunovmartin.bsky.social · May 16

10/ So grateful to @thejop.bsky.social and all who supported this work since it began as a first-year seminar paper (!)

1 4

Martin Naunov @naunovmartin.bsky.social · May 16

9/ I call for a methodological shift in studying discrimination: away from simple, text-based cues that reduce identity to a census box. Facial & vocal stimuli better reflect how we perceive difference and categorize others in the real world—& can help uncover bias at both group and subgroup levels.

1 4

Martin Naunov @naunovmartin.bsky.social · May 16

8/ In particular, we must look beyond group-level biases (e.g., gay vs. straight, Black vs. white) and attend to how ppl respond to subsets within minority groups—those who refuse or fail to “cover” distinct markers of their known minority identity and culture, like hairstyle, speech, or clothing.

1 5

Martin Naunov @naunovmartin.bsky.social · May 16

7/ While focused on sexual orientation, I hope this study speaks to & has important takeaways for research on status, prejudice, discrimination, and respectability politics more broadly.

1 4

Martin Naunov @naunovmartin.bsky.social · May 16

6/ This finding underscores the value of recalibrating our empirical approach to studying LGBTQ politics and disparities, paying closer attention to insights from queer and political theory that identify heteronormativity, not heterosexuality per se, as the central axis of power and exclusion.

1 6

Martin Naunov @naunovmartin.bsky.social · May 16

5/ Gender nonconformity biases disproportionately affect sexual minorities. Still, I argue & find that straight candidates with relatively gender nonconforming traits also fall near or outside the bounds of heteronormativity and, as a result, face discrimination.

1 5