iiinova — where your digital self keeps evolving

Alexander Agadjanian @agadjanian.bsky.social · 27/09/2026

Really interesting paper that builds on how politics can shape social identities link.springer.com/article/10.1... Experiment on Christians: politician promoting Christian Nationalism doesn't affect IDing with that label, but a pol rejecting it causes people to disassociate from that ID

010

Alexander Agadjanian @agadjanian.bsky.social · 10/09/2026

Another good lesson in questioning assumptions about core social science variables often seen as fixed and exogenous huber.research.yale.edu/materials/12...

0134

Alexander Agadjanian @agadjanian.bsky.social · 02/09/2026

My last APSA commitment ends right when Chelsea Arsenal begins. If you’re around and interested, please let me know if you’d like to catch the match somewhere! (And feel free to come to the great panel I’m on I guess)

021

Alexander Agadjanian @agadjanian.bsky.social · 20/08/2026

Interesting - not just one sign of partisan voting behavior and heuristic following (ticket splitting) diminishes in governor races, looks like party leader influence does too

000

Reposted by Alexander Agadjanian

G Elliott Morris @gelliottmorris.com · 13/08/2026

I have reanalyzed polling microdata from two surveys in Wisconsin, generously shared with me by State Navigate, and put the results up Strength In Numbers for all to learn from. As far as I know this is the only public autopsy from Tuesday's miss www.gelliottmorris.com/p/2026-08-13...

gelliottmorris.com

I re-analyzed the raw data from Wisconsin's primary polls. Here's what actually went wrong.

What raw data from Wisconsin's Democratic primary reveals about demographic weighting, late movement, and who answers polls

1529789

Alexander Agadjanian @agadjanian.bsky.social · 04/08/2026

Two very interesting papers on how minorities respond to exclusion (having IDs not represented in info + categories presented to them). Somewhat different treatments and outcomes, and diff populations, but I think very parallel in spirit -- one account of mobilization, the other demobilization

2147

Alexander Agadjanian @agadjanian.bsky.social · 06/06/2026

Very religious bent to course evals this year for intro stats class 🤔 (course eval q was "What advice would you give to another student who is considering taking this course?")

070

Alexander Agadjanian @agadjanian.bsky.social · 31/10/2025

Department floor is having a halloween door decor contest, I think our office wins for scariest @antoniaalksnis.bsky.social

051

Reposted by Alexander Agadjanian

Tiago Ventura @tiagoventura.bsky.social · 07/10/2025

Our conclusion is that survey professionalism is widespread on online panels, but these do not, by and large, distort inferences, making us cautiously optimistic about research using these online samples!

2101

Alexander Agadjanian @agadjanian.bsky.social · 07/05/2025

Very creative & well-done new @thejop.bsky.social: 🇩🇪 far-right support ⬆️ among people living near outdoor swimming pools when you enter summer months (when these pools become popular) -- but only in areas that have more immigrants. www.journals.uchicago.edu/doi/abs/10.1...

171

Reposted by Alexander Agadjanian

eric gonzalez juenke @egojunk.bsky.social · 17/04/2025

Good update with a different data point from @agadjanian.bsky.social

In recently released CES 2024 data, looking at presidential vote choice...

Ages 18-21: 58% Harris, 38% Trump
Ages 22-29: 58% Harris, 38% Trump

Zero difference. Not directly comparable (cited poll is April, CES data from late 2024) but unlikely so much has changed since then.

2144

Alexander Agadjanian @agadjanian.bsky.social · 07/04/2025

Biennial update on racial resentment trends in the CES: after a white Dems shift *away* from racially liberal trajectory in 2022, we're back in that direction in 2024.

03010

Alexander Agadjanian @agadjanian.bsky.social · 24/03/2025

Interesting new JEPS on POC solidarity building. Besides substantive contribution, another example of getting creative with experiments to learn about mechanisms (vs. conventional mediation analysis-only). On a very different topic, here's another good example along these methodological lines

120

Alexander Agadjanian @agadjanian.bsky.social · 02/03/2025

Interesting new paper on this topic (www.journals.uchicago.edu/doi/10.1086/...) -- misinfo itself has more direct, widespread consequences, but factual beliefs again seem to be outside of the equation

110

Alexander Agadjanian @agadjanian.bsky.social · 15/01/2025

Two good places to donate for supporting LA wildfire relief efforts: 1. Eaton Fire Relief and Recovery Fund (from Pasadena Community Foundation) pasadenacf.org/supporting-o... 2. Immigrant Fire Relief Fund (from National Day Laborer Organizing Network) secure.actblue.com/donate/lafir...

pasadenacf.org

Supporting Our Community: Eaton Canyon Fire Relief & Recovery Fund | Pasadena Community Foundation

Dear Pasadena Community Foundation Family, We have all been glued to the news watching the devastation of the Eaton Canyon fire to our neighbors. My heart g ...

010

Reposted by Alexander Agadjanian

Miguel Pereira @miguelpereira.bsky.social · 05/12/2024

APSR will start inviting replications for a random subset of accepted papers. I really like this as well as the constructive tone around it 👏 (from the latest Notes from the Editors)

414046

Reposted by Alexander Agadjanian

Alex Coppock @aecoppock.bsky.social · 05/12/2024

texans against multiple outcome measures

3474

Alexander Agadjanian @agadjanian.bsky.social · 27/12/2024

Interesting perspectives. Feels like some disconnect from standard polisci accounts (e.g. effects of misinfo/fact-checks often have limited scope, but that doesn't mean misinfo is overall inconsequential www.pnas.org/doi/abs/10.1...). Was also curious about this part and dug around on the cites...

5163

Alexander Agadjanian @agadjanian.bsky.social · 23/12/2024

Friends don't let friends capture operational ideology via self-described ideological ratings, a series

140

Alexander Agadjanian @agadjanian.bsky.social · 16/12/2024

Super valuable new study that randomly assigns 7k+ Americans to old vs. new Census race formats. Among many interesting patterns: 1. White & "some other race" %'s ⬇️ by 6 and 4 pts. 2. No change in overall Hisp and Black %'s. 3. Small but detectable ⬇️ Black + Hisp responses.

165

Reposted by Alexander Agadjanian

Jake Grumbach @jakemgrumbach.bsky.social · 01/12/2024

“East Bay hot, South Bay not” was apparently a popular saying in like the 80s and I’m gonna bring it back

4221

Reposted by Alexander Agadjanian

jon ben-menachem @jbenmenachem.com · 25/11/2024

Just now seeing this paper reanalyzing the "Many Teams" paper on racial bias in soccer (29 teams analyze the same RQ with the same data, find different results). This reanalysis finds that variation in findings results from theoretical / interpretive differences. journals.sagepub.com/doi/full/10....

journals.sagepub.com

Has the Credibility of the Social Sciences Been Credibly Destroyed? Reanalyzing the “Many Analysts, One Data Set” Project - Katrin Auspurg, Josef Brüderl, 2021

In 2018, Silberzahn, Uhlmann, Nosek, and colleagues published an article in which 29 teams analyzed the same research question with the same data: Are soccer re...

35011

Reposted by Alexander Agadjanian

Amanda Sahar d’Urso @asdurso.bsky.social · 15/11/2024

REP Starter Pack go.bsky.app/GxR7Bkf

188138

Reposted by Alexander Agadjanian

Joe Noonan @joenoonan.se · 27/08/2024

What are some good examples of political science papers using observational data published with null results?

562

Reposted by Alexander Agadjanian

Alex Coppock @aecoppock.bsky.social · 23/05/2024

Here's a nice new paper from the fully blueskyless author team of Philip Moniz, Rodrigo Ramirez-Perez, Erin Hartman, and Stephen Jessee, showing that survey exp. effects are similar for "eager" and "reluctant" respondents, with positive implications for generalizability doi.org/10.1017/pan....

Table 1 An analysis of treatment effect heterogeneity. We conducted an omnibus test provided in the grf R package. We also compared the estimates among eager and NRFU respondents. Most studies show no statistically significant treatment effect heterogeneity in either test (Neither). Ten show evidence of heterogeneity using the omnibus test, but it is not driven by differences between eager and NRFU respondents (Omnibus Only). Two studies show no evidence using the omnibus test, but do display NRFU-specific heterogeneity (NRFU Only), and two others display both general and NRFU-specific effect heterogeneity (Both).

Figure 2 Standardized ATEs among reluctant and eager respondents closely resemble each other. Points show estimated treatment effects estimated separately among eager and reluctant respondents, with 95% confidence interval bars. Solid line shows Deming regression fit and shaded region shows its block-bootstrapped 95% confidence region.

02110

Reposted by Alexander Agadjanian

Dave Karpf @davekarpf.bsky.social · 10/03/2024

I did not attend UNC, but I did attend *America.* So you’re damn right I’m rooting for UNC tonight.

512413

Alexander Agadjanian @agadjanian.bsky.social · 07/01/2024

It's wild to see some 2024 election polls show Hispanic vote split almost evenly across Biden/Trump (e.g. twitter.com/Nate_Cohn/st...) Took a quick look at what various polls in last month show + how they compare to same time last cycle (Dec. 2019). For 2024, even split is actually not that typical

110

Alexander Agadjanian @agadjanian.bsky.social · 31/12/2023

For any Premier League fans out there: a look at team performance relative to what we'd expect from expected goals now that we're ~halfway through the season. Hoping some of this underperforming (Chelsea) and overperforming (Tottenham) balances out the rest of the way 😬

011

Alexander Agadjanian @agadjanian.bsky.social · 02/12/2023

More on genetic ancestry tests from a great new American Journal of Sociology piece (using an RCT): these tests have important consequences for facets of whites' identities, but notably *do not* cause changes to how whites racially self-identify www.suleyaylaci.com/wp-content/u...

23714

Alexander Agadjanian @agadjanian.bsky.social · 22/11/2023

Me watching another paper I reviewed eventually get accepted for publication while still working through some roadblocks in my own research

030

Alexander Agadjanian @agadjanian.bsky.social · 21/11/2023

Are presidential election polls predictive this far out from election day? Lot of skepticism, but as @gelliottmorris.bsky.social and I have shown, current era might contrast from earlier decades, e.g. poll predictiveness didn't change much over ~year before 2016. An update to now include 2020...

111

Alexander Agadjanian @agadjanian.bsky.social · 11/11/2023

Really great, comprehensive paper on consequences of popular pro-police TV shows: -cops make more victimless crime+drug possession arrests when followed by cameras -no impact on public safety (solved crimes, amt of crime) -some public attitudes around police improve papers.ssrn.com/sol3/papers....

001

Reposted by Alexander Agadjanian

Jason "Red5" Lyall @jaylyall.bsky.social · 01/11/2023

Between 38,200 and 44,500 buildings throughout the Gaza Strip (about 14% of all buildings in Gaza, and 25% of northern Gaza) have been damaged or destroyed since the war's beginning, new study finds. One of the most intense bombing campaigns of the 21st century by sorties/time & civilian casualties

nytimes.com

Maps: Tracking the Attacks in Israel and Gaza

At least a quarter of all buildings in northern Gaza are damaged or destroyed, a satellite analysis suggests.

9299220

Alexander Agadjanian @agadjanian.bsky.social · 31/10/2023

A classic case of the Monday’s for someone in our department, you hate to see it

100

Alexander Agadjanian @agadjanian.bsky.social · 29/10/2023

Last time USC football comes to Berkeley (RIP Pac-12)… never in doubt!!! (Just kidding it was, this team takes years off my life even though the season’s now meaningless 👍 👍 👍)

020

Alexander Agadjanian @agadjanian.bsky.social · 28/10/2023

Far from most important thing about this right now, but a check-in on partisan public opinion around Israel/Palestine (from earlier this year, to immediate reaction, to a few weeks on): -everyone's making their minds up more (not sure ⬇️) -for Ds & Is, this means warmer to Palestine, for Rs, opposite

111

Alexander Agadjanian @agadjanian.bsky.social · 25/10/2023

Current bus options for commuting to dept in Berkeley (left) vs. when I was going to work in Boston (right). Take me back, I want to have a positive relationship with public transportation again 😭

020

Reposted by Alexander Agadjanian

donni saphire @donni.bsky.social · 22/10/2023

You should stay up and read more internet. You’re just getting to the good part

212647711

Reposted by Alexander Agadjanian

Alexander Wuttke @kunkakom.bsky.social · 19/10/2023

In case you missed it, polisky: *The Journal of Politics continues to accept Registered Report submissions until the end of June* We have extended the trial period🙂 (At the end of the year this team's editorial term will then run out) *Stats* 33 Submissions so far 2 In-Principle-Accepted Studies

2248

Reposted by Alexander Agadjanian

Alex Coppock @aecoppock.bsky.social · 19/10/2023

I think most important findings from this study: 1) We confirm misinfo increases false beliefs, fact checks decrease them, for Rs and Ds both. 2) Some personality and cognitive measure correlate with the magnitudes, we think because they correlate with attention to the fact-check.

Figure 3. Effects by party.
Notes: Points are the predicted effects by partisanship. Ranges indicate 95 per cent confidence intervals. Points are increased in size, and labelled, when an effect is significantly different to 0 (at p < 0.05). Partisan differences in correction or misinformation effects are depicted with asterisks. *** p < 0.001; ** p < 0.01; * p < 0.05.

Figure 5. Heterogeneous treatment effect estimates.
Notes: Each small point is an underlying effect estimate for some potential source of effect heterogeneity (each source is described on the y-axis). Effects for those with low values are depicted with dark points; effects for those with high values are depicted with light points. Larger points, labels, and line ranges are meta-analytic summaries of these distributions. Significance levels report when these meta-analytic estimates are different. *** p < 0.001; ** p < 0.01; * p < 0.05.

22313

Reposted by Alexander Agadjanian

Joe Noonan @joenoonan.se · 19/10/2023

Survey experiments are ubiquitous in political science. But I have only found two articles assessing their external validity (Barabas and Jerit (2010) and Hainmueller et al (2015)). Am I missing some key literature here? [polisky]

102512

Alexander Agadjanian @agadjanian.bsky.social · 18/10/2023

Dispatch from a department reply all email chain: we’re now on email #4 about how to get the printer to work. Not sure if reply all’s are intentional. A natural end is in sight but I worry about the pace of email replies coming in. Only time will tell.

030

Alexander Agadjanian @agadjanian.bsky.social · 17/10/2023

19th year anniversary, mandatory viewing today... I miss postseason baseball www.youtube.com/watch?v=_9Kx...

010

Alexander Agadjanian @agadjanian.bsky.social · 16/10/2023

Our dept is hearing this talk later this week. Super interesting in and of itself but also in relation to other misperceptions work: this pattern of corrective info (a) affecting factual beliefs but (b) not affecting attitudes/behaviors is remarkable in how often it appears (& what it might imply)..

171

Reposted by Alexander Agadjanian

Brendan Nyhan @brendannyhan.bsky.social · 14/10/2023

Poli sci leading the way among social sciences on sharing data/code; behind psych on preregistration.

4409

Alexander Agadjanian @agadjanian.bsky.social · 14/10/2023

A buggy whip throwback at a social science journal in the year 2023 statmodeling.stat.columbia.edu/2014/08/06/p...

184