Eric T. Plutzer

@JustinWolfers @natesilver Nate Silver is taking pollster's published margins of error at face value. The effect of weighting on past vote should be a dampening of the sampling variance -- very similar to the "first stage ratio adjustment" used in institutional surveys such as the monthly BLS jobs report.

Point is, @NateSilver dramatically over-estimates the margin of error of many modern polls. His estimates are more than two times as wide as they should be. And that's why he finds so few "outlier" polls *relative to what the tails of his naive distribution tell him to expect*

Lately @NateSilver has been arguing that pollsters are "herding" —tweaking or hiding their results to avoid publishing outliers. I don't know any (reputable) pollsters who do this. And I think the problem here is Nate making a simple math/stats error 🧵

Democracy on the ballot, in more ways than one. mprnews.org/story/2024/10/… New @McCourtneyInst / @APMResearch Mood of the Nation Poll.

@polpsychjoe Pretty clear that Trump's 2020 record number of national votes for a losing candidate was due to mobilization of peripheral voters (not habitual and not newly registered). They stayed home for special elections and reproductive rights ballot initiatives.

Which is a better interpretation - that Dems have an advantage from habitual voters, or that Republicans can expect a boost from peripheral voters? (I imagine most of those who voted in 1 election voted in 2020).

not an RCT so obviously can’t claim causality. If anything it’s probably bookings causing the eclipse

Please join us in congratulating @CEU_iUfU on receiving the 2024 Brown Democracy Medal! Invisible University's work follows a long tradition of underground universities as acts of democratic defiance amid conflict and rising authoritarianism. psu.edu/news/liberal-a…

(cc: @itserinfitz) Our soon-to-be-out article, coming soon to a Public Opinion Quarterly volume near you, might have something to say about all this... osf.io/preprints/psya…

"The Rhetorical 'What Goes with What': Political Pundits and the Discursive Superstructure of Ideology in U.S. Politics" is conditionally accepted at Public Opinion Quarterly: osf.io/vwqnf

In this article in Public Opinion Quarterly, researchers introduce a revised hostile sexism scale for better measurement accuracy. Item-specific format improves validity, recommending adoption by researchers. Learn more: bit.ly/43fBKz6

@NateSilver538 "Consensus" is the wrong concept: That many think one explanation is more likely than another when neither has strong, direct evidence is nothing like the consensus that multiple, independent lines of evidence show greenhouse gasses contribute to global temperature rise.

This is not a scientific way to do a survey. The biggest issue is that it involved personalized outreach based on a totally arbitrary set of criteria. That's a *huge* no-no. It also, by design, had very few biosafety or biosecurity experts. gcrinstitute.org/papers/069a_co…

Great piece!

Very excited that POQ will devote it's upcoming special issue to qualitative research on public opinion, civic behavior, elections, political communication or any other topic within our usual scope. Pass the word!

@McCourtneyInst Is there a transcript?

ICYMI: President Bendapudi's video on free speech is worth watching as we enter a new school year and an election season. psu.edu/news/administr…

@b_schaffner Huge shifts. Thanks for posting. I'm guessing at least a small part is entangled with shifts to the south, and growing proportions of higher skilled workers (as some positions automate). But hard to see anything other than partisan change being the lion's share of explanation.

a decade ago, Americans in the manufacturing, construction, and transportation/warehousing were more likely to identify as Democrats than Republicans. that has definitively changed

A bipartisan majority of Americans support universal background checks and gun licensing. A majority also supports an assault weapons ban, but support is more partisan mprnews.org/story/2023/07/… by @McCourtneyInst's @ericplutzer & @APMResearch's @rithwik_kalale & me via @MPRnews

"In the last few years, we have come to understand that democracy is hard work, that it requires a lot from all of us, and that it's fragile." - @cbeem1 in the @AP as part of a story on a new Associated Press-NORC Center for Public Affairs Research poll. #1" target="_blank" rel="nofollow noopener">wfmz.com/news/americans…

There is still time to apply for a journal editor or associate editor position! buff.ly/3qqvZPO

@Penn_state's @ericplutzer explains: “There are two very different ways Americans are pushed away from political discussion. The first is lack of interest... The other is deliberate avoidance, even if they are interested." apmresearchlab.org/motn/poll-demo…

My latest, just in time for #4thofJuly laist.com/news/politics/… via @LAist @APMResearch's analysis of new @McCourtneyInst Mood of the Nation Poll data finds that 3 in 4 of Americans endorse democracy, but only 16% say they feel comfortable talking about politics with everyone

.@APMResearch's analysis of NEW @McCourtneyInst Mood of the Nation polling data via @MPRnews mprnews.org/story/2023/07/… Among the findings: 1 in 8 Americans (13%) avoid talking about politics with their spouse or romantic partner #4thofJuly

Congrats to Morrgan Herlihy, a @psupolisci student whose research on state politics and federal judicial selection you should watch out for, on being the inaugural @McCourtneyInst Roosevelt Fellow. You can read more about Morrgan and the fellowship here: psu.edu/news/liberal-a…