Andrew Trexler

Andrew Trexler

@atrexler.com

Assistant professor. | He/his. | Political communication, political behavior, news media, public opinion, survey methods. | atrexler.com | Opinions own.

753 followers378 following183 posts

Andrew Trexler reposted

John V. Kane
@uptonorwell.bsky.social

๐Ÿ—“๏ธ ๐ƒ๐จ ๐ฒ๐จ๐ฎ ๐จ๐ซ ๐ฒ๐จ๐ฎ๐ซ ๐ฌ๐ญ๐ฎ๐๐ž๐ง๐ญ๐ฌ ๐๐จ ๐ฌ๐ฎ๐ซ๐ฏ๐ž๐ฒ ๐ž๐ฑ๐ฉ๐ž๐ซ๐ข๐ฆ๐ž๐ง๐ญ๐ฌ? On 12/3, I'm hosting a free, 1 hr. online seminar called, "Doing Better Survey Experiments" from 1pm - 2pm (ET). Please help spread the word if you can! ๐Ÿ™ instats.org/seminar/doin...

instats.orgDoing Better Survey Experiments (Free Seminar) - Livestreamed Research Training | InstatsPhD-level seminar on Doing Better Survey Experiments (Free Seminar) with John Kane . Live Q&A plus onโ€‘demand access. Join via your universityโ€™s Instats membership or enroll directly.

Andrew Trexler reposted

Matthew Pietryka
@mtp.bsky.social

Dear Elections, Public Opinion, and Voting Behavior scholars: Join us in Madison on the terrace! It is lovely here in May.

Barry Burden@bcburden.bsky.social

The fifth annual EPOVB conference will take place @uwmadison.bsky.social on May 13-14, 2027! Submit your paper & poster proposals by the Dec 1 deadline. Supported by @epovb.bsky.social & @electionscenter.bsky.social The proposal form & conference information here: elections.wisc.edu/epovb27/

Andrew Trexler reposted

Stephen Vaisey ๐Ÿ‡บ๐Ÿ‡ฆ
@stephenvaisey.com

BTW this means no funding for GSS, ANES, or PSID. GSS 2026 is in the field now, but then it looks like that's it. Devastating for social science.

Dan Garisto@dangaristo.bsky.social

NEW: In March the White House released an FY27 budget request that zeroed out the National Science Foundation's directorate of Social, Behavioral and Economic Sciences (SBE). For months it was unclear what would happen. Now, with FY26 over, the damage to SBE is coming to light. My reporting:

science.orgโ€˜Complete devastationโ€™: How NSF gutted its social sciences researchAgency body that funds sociology, linguistics, and archaeology studies in U.S. gave 90% fewer new grants this year

Andrew Trexler reposted

Isabella Rebasso
@isabellareb.bsky.social

New paper with Yanna Krupnikov out in Political Communication! ๐ŸŽ‰ We know moral-emotional content ("moral outrage") spreads fast on social media. But does that mean people actually want to see it? We tested whether people select this content when given the choice - turns out, not really.

tandfonline.comRethinking Assumptions About Moral Content Selection: Moral-Emotional Content May Be Less Appealing Than AssumedRecent work has shown that moral-emotional content spreads rapidly on social media platforms such as X (Twitter). These patterns have led to concerns that social media facilitates the spread of mor...

Andrew Trexler reposted

Adam Bonica
@adambonica.bsky.social

The fundraising texts you delete are working on someone. Itโ€™s infuriating and heartbreaking. An 85yo in Ohio gave more than double the value of his home. A 91yo in an Indianapolis senior facility gave 25K times. The DCCC/DSCC donโ€™t just tolerate the spammers who exploit seniors. They take part.

data4democracy.substack.comHook and SqueezeHow Democratic consultants, committees, and party leaders built a fundraising spam pipeline that funnels money from a captive pool of elderly donors into their own operations.

Andrew Trexler reposted

John V. Kane
@uptonorwell.bsky.social

๐ŸšจSuper excited to share this new WP with Joohye Jeong, @adamberinsky.bsky.social, Soong & Parker. We ask a simple but extremely practical Q for survey researchers: ๐ƒ๐จ๐ž๐ฌ ๐ข๐ญ ๐ฆ๐š๐ญ๐ญ๐ž๐ซ ๐ฐ๐ก๐ž๐ซ๐ž ๐ฐ๐ž ๐ฉ๐ฅ๐š๐œ๐ž ๐ข๐ญ๐ž๐ฆ๐ฌ/๐ž๐ฑ๐ฉ๐ž๐ซ๐ข๐ฆ๐ž๐ง๐ญ๐ฌ ๐ข๐ง ๐จ๐ฎ๐ซ ๐ฌ๐ฎ๐ซ๐ฏ๐ž๐ฒ? Answer: Not really, no. ๐Ÿ‘

Andrew Trexler reposted

Jay Van Bavel, PhD
@jayvanbavel.bsky.social

We need to change norms around sexual harassment Yesterday Tessa West spoke up about a sexual harassment complaint she filed against John Jost. Not only is he a senior colleague in the dept of psychology, but he is one of the most prominant figures in the field of social and political psychology.

Andrew Trexler reposted

Petter Tรถrnberg
@pettertornberg.com

โ€˜Polarizationโ€™ has become the master concept for diagnosing our current democratic crisis. But this is not polarization. It is the radicalization of the political right. By misdiagnosing it, we risk becoming complicit in the crisis. ๐Ÿงต Just out in Perspectives on Politics doi.org/10.1017/S153...

Andrew Trexler reposted

LSE US Politics and Policy blog - USAPP
@lseusablog.bsky.social

Expanding mail voting in 2020 helped more people in all racial groups to vote by mail, but its effect on government trust is less clear find @maraynam.bsky.social , @atrexler.com and @profsorelle.bsky.social blogs.lse.ac.uk/usappblog/20...

blogs.lse.ac.ukExpanding mail voting in 2020 helped more people in all racial groups to vote by mail, but its effect on government trust is less clear | LSE United States Politics and PolicyExpanded access to mail voting increased peopleโ€™s decisions to cast their ballots by mail across all racial groups.

Andrew Trexler reposted

Nature Human Behaviour
@nathumbehav.nature.com

Representativeness and response validity across nine opt-in online samples

dlvr.itRepresentativeness and response validity across nine opt-in online samplesNature Human Behaviour, Published online: 22 June 2026; doi:10.1038/s41562-026-02438-zStagnaro et al. compare nine opt-in participant samples on measures of response validity, representativeness and professionalism. They find substantial variation across samples and offer guidance for choosing samples based on the research question.

Andrew Trexler reposted

Barry Burden
@bcburden.bsky.social

My department @uwpolisci.bsky.social is hiring an assistant professor with expertise in environmental politics jobs.wisc.edu/jobs/assista...

jobs.wisc.eduAssistant Professor of Political Science - RISE EARTH - Madison, Wisconsin, United StatesCurrent Employees: If you are currently employed at any of the Universities of Wisconsin, log in to Workday to apply through the internal application process.Job Category:FacultyEmployment Type:Regula...

Andrew Trexler reposted

Genevieve Bates
@genbates.bsky.social

๐Ÿšจ ๐ŸšจCalling all #polisky grad students who presented at #ISA2026: I'm chairing the committee for the Human Rights Sectionโ€™s Steven C Poe best grad student paper award. We are currently accepting nominations, including self-nominations, and all you have to do is email your paper to me!

Andrew Trexler reposted

Barry Burden
@bcburden.bsky.social

My department is hiring an assistant professor in political theory with a focus on American political thought and/or American constitutionalism jobs.wisc.edu/jobs/assista...

jobs.wisc.eduAssistant Professor of Political Science - Madison, Wisconsin, United StatesCurrent Employees: If you are currently employed at any of the Universities of Wisconsin, log in to Workday to apply through the internal application process.Job Category:FacultyEmployment Type:Regula...
Andrew Trexler
@atrexler.com

Seeing lots of "voters are dumb" takes on this, Converse laser-eyes, etc. Consider the survey-taking experience. Ppl see/interpret these individually and give atomized answers. Q1: What will make Ds electable? Move to center. Q2: Is D party radical? No. Q3: Your personal view? Socialism = good.

G Elliott Morris@gelliottmorris.com

A new poll from the New York Times shows potential Democratic voters want the party to move to the right, are happy with where it is ideologically, and rate socialism highly. Huh? www.gelliottmorris.com/p/2026-06-12...

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

View full thread
Andrew Trexler
@atrexler.com

Our results: First, we find consistent evidence that RM designs attenuate ATE estimates by roughly ~20%. At the same time, PO designs are imprecise, requiring a large N for a reliable estimate. RM designs offer very large precision gains, by ~50% in our samples (note: N matters here).

Andrew Trexler
@atrexler.com

Worth clarifying: N matters in the sense that the benefit to power from the % reduction in the SE decreases as N grows (see Fig 6). N matters little for the % change magnitude directly. For RQs about magnitude, absolute error is a more central consideration (see Fig 7).

Andrew Trexler reposted

Alexander Wuttke
@kunkakom.bsky.social

Cumulative science at its best.

Andrew Trexler@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

View full thread
Andrew Trexler
@atrexler.com

We conclude RM designs serve as a better default than PO designs. Social science engages with small effects, is resource limited, & often concerns directional tests. RM designs are better in these settings, though cases remain where large-N PO designs are better (magnitude RQs, sensitive topics).

Andrew Trexler
@atrexler.com

Thanks for reading! We're very excited about this one; we were all grad students when this project began & it came a long way w/lots of help. Thanks to TESS, Rapoport, & Bass for $, to NORC for helping field, to many folks for helpful comments, & Scott/Geoff esp. throughout (true model replicatees)!

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

View full thread
Andrew Trexler
@atrexler.com

That said, we find initial evidence that the design effect increases as respondents are repeatedly exposed to RM designs within a single survey, and particularly when attitude-recall questions (asking Rs to recall their pre-treat attitude) are deployed. This has implications for omnibus surveys.

Andrew Trexler
@atrexler.com

In our last analysis, we use simulations grounded in our observed data to investigate the bias-precision tradeoff. RM designs always offer superior power; this benefit declines as N-per-arm gets large. Yet RMs will be more accurate to true ATEs in expectation unless PO designs are very well powered.

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

View full thread
Andrew Trexler
@atrexler.com

Our results: First, we find consistent evidence that RM designs attenuate ATE estimates by roughly ~20%. At the same time, PO designs are imprecise, requiring a large N for a reliable estimate. RM designs offer very large precision gains, by ~50% in our samples (note: N matters here).

Andrew Trexler
@atrexler.com

Second, we observe few differences in the design effect by sample type (prob/nonprob), design type (between-groups/within-subject), and even by how close together repeated measures appear. RM design effects are no worse when putting pre-treatment measure, treatment, post-treatment back-to-back.

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

View full thread
Andrew Trexler
@atrexler.com

Scholars often prefer PO designs out of concern that pre-treatment measures may bias the estimate of the average treatment effect (via consistency pressures, priming, or demand effects). Clifford, Sheagley, & Piston (2021) provide evidence that these concerns are unwarranted: doi.org/10.1017/S000...

doi.orgIncreasing Precision without Altering Treatment Effects: Repeated Measures Designs in Survey Experiments | American Political Science Review | Cambridge CoreIncreasing Precision without Altering Treatment Effects: Repeated Measures Designs in Survey Experiments - Volume 115 Issue 3
Andrew Trexler
@atrexler.com

What we do: 1. Partially replicate CSP with 6 studies each fielded on 3 distinct samples (18 studies, 13163 participants, 78978 total obs). 2. Increase evidence on within-subject designs 43-fold. 2. Compare probability & non-prob samples. 3. Randomize how close repeated measures appear together.

Andrew Trexler
@atrexler.com

Thrilled to announce my paper with @dianamejordan.bsky.social & sky-less Trent Ollerenshaw is now published open-access at @apsrjournal.bsky.social. In a (very) large replication & extension, we show that design effects of repeated measure experiments are nonzero but typically small. Thread:

Cambridge University Press Political Science & IR@cambup-polsci.cambridge.org

#OpenAccess from @apsrjournal.bsky.social - New Evidence and Design Considerations for Repeated Measure Experiments in Survey Research - https://cup.org/4sVtFLj - @dianamejordan.bsky.social, TRENT OLLERENSHAW & @atrexler.com #FirstView

Andrew Trexler
@atrexler.com

First, a quick preview of the findings: 1. Repeated measure designs attenuate ATE estimates by ~20% on avg relative to classic post-only measurement. 2. RM designs also provide massive gains in statistical power. 3. For most applications, power gains will trump ATE attenuation, so use RM designs.

Andrew Trexler
@atrexler.com

Background: classic post-only experiments randomize & deliver treatment, then measure outcomes only post-treatment. Repeated measure designs measure the outcome both pre- and post-treatment. (Within-subject variants deliver multiple treatments & measure outcomes multiple times.)