Sign in

Pollcat, AKA Scott Keeter

@pollcat.bsky.social
2.1K followers 1.2K following 33 posts

Part-time survey advisor at Pew Research Center, hiker, bad golfer, hoops fan

PostsRepliesMedia
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 30/09/2026
Can AI models replace traditional polling? New report from colleagues at Pew Research Center finds that AI-generated survey results struggled to accurately reproduce the findings from high-quality public opinion polls in a variety of ways. Read more www.pewresearch.org?p=549336
pewresearch.org
Can AI Stand In for Human Survey-Takers? Not Really
Synthetic surveys using digital twins do a poor job estimating the public mood and are especially error-prone for some subgroups, including Republicans and Black adults.
083
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 16/09/2026
@awmercer.bsky.social might have more to say about this but changing party ID itself should not bias the past vote weighting. But it could do so if there is a tendency for people who've shifted their party ID to misremember or misreport their past vote, which is indeed a known kind of bias
110
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 16/09/2026
Three ways to correct a poll’s political balance: weight on self-reported party affiliation, self-reported past vote, or voter file data such as party registration. Each has strengths and weaknesses. No one approach is clearly superior in all contexts.
000
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 16/09/2026
There is growing evidence that Republicans have become somewhat less likely than Democrats to participate in polls, particularly around presidential elections. But the need to do so has risen and the tools available to do it have gotten better.
110
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 16/09/2026
There are good arguments against weighting polls on past vote or party affiliation. We know because we’ve made many of those arguments over the years
100
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 16/09/2026
Almost 70% of national polls in 2024 were weighted on party affiliation or past vote. This kind of political weighting is controversial. But evidence shows it has made polls modestly more accurate. New report: how it works, how we do it and its limits: www.pewresearch.org/methods/2026...
pewresearch.org
Weighting Polls on Party Affiliation and Past Vote
This report explains how political weighting works, how Pew Research Center does it, and some of its limitations.
21413
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 27/08/2026
Bogus or fraudulent respondents constitute one of the most urgent problems in online opt-in polling. This new report by my colleague Andrew Mercer looks at three methods to identify bogus cases but finds no surefire solution www.pewresearch.org/methods/2026...
pewresearch.org
No Easy Fix for Bogus Respondents in Online Opt-In Polls
A new study examining online opt-in polling finds that while removing bogus respondents generally improves data quality, no single method reliably solves the problem.
0134
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 10/06/2026
Where do you fit in the new political typology? Give our new quiz a try: www.pewresearch.org/politics/qui...
pewresearch.org
Political Typology 2026
Take our quiz to find out which one of our nine political typology groups is your best match.
000
Reposted by Pollcat, AKA Scott Keeter
Pew Research Center @pewresearch.org · 10/06/2026
Do you feel like you don’t fit in as a ‘Democrat’ or a ‘Republican?’ Our new political typology shows this complexity, sorting the public into nine distinct groups based on their political and cultural values. The result is a picture of American politics with far more than just red and blue.
Chart of The 2026 Pew Research Center Political Typology.
63616
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 29/10/2025
This AAPOR report is amazingly comprehensive. It's based on a massive data collection effort that compiled polling across elections at various levels and geographies extending back to 2000.
030
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 29/10/2025
Major conclusions:
2167
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 29/10/2025
The AAPOR Task Force on 2024 Pre-Election Polling has released its final report today. aapor.org/wp-content/u...
aapor.org
175
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 23/07/2025
Today's release of the 2025 NPORS survey and data wasn't the only thing we were up to. Here's a piece on why we decided to add past vote to our survey weighting and how it's done www.pewresearch.org/decoded/2025...
pewresearch.org
Why and how we’re weighting surveys for past presidential vote
This piece explains why, when and how we are weighting our surveys on Americans’ past vote.
083
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 23/07/2025
And here are party affiliation trends from six years of NPORS data www.pewresearch.org/politics/fac...
pewresearch.org
Party Affiliation Fact Sheet (NPORS)
Explore trends in partisan identification among U.S. adults using data from Pew Research Center’s National Public Opinion Reference Survey (NPORS).
020
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 23/07/2025
Calling all data nerds! Pew Research Center has just released its 2025 edition of the National Public Opinion Reference Survey, with estimates of U.S. party affiliation, religious affiliation and frequency of internet use. Fact sheet and links to the dataset: www.pewresearch.org/methods/fact...
pewresearch.org
National Public Opinion Reference Survey (NPORS)
NPORS is an annual survey of U.S. adults conducted by the Pew Research Center used to to produce benchmark estimates for several topics.
172
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 08/05/2025
We took a broad look at social trust in America today. With a survey of almost 37,000 people we were able to look at levels of trust across the states and even in metro areas. Check out our new report here www.pewresearch.org/SocialTrust
pewresearch.org
Americans’ Trust in One Another
Americans trust each other less than they did a few decades ago. We explore why this is, and why some are more trusting than others.
11613
Reposted by Pollcat, AKA Scott Keeter
Laura Silver @lauraruthsilver.bsky.social · 08/04/2025
NEW from @pewresearch.org today: Americans Give Early Trump Foreign Policy Actions Mixed or Negative Reviews www.pewresearch.org/global/2025/... Below, a thread of some key findings
pewresearch.org
Americans Give Early Trump Foreign Policy Actions Mixed or Negative Reviews
More disapprove than approve of leaving the WHO and ending USAID. About half see tariffs on China as bad for the U.S. and them personally, but views differ by party.
132
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 07/04/2025
Here's a great starter pack filled with some of my wonderful colleagues at @pewresearch.org Give 'em a follow!
040
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 21/03/2025
You probably don't often turn to the survey methodology world for a good detective story, but here is one from my colleague Anna Brown pewrsr.ch/4isAu2s
pewrsr.ch
How a glitch in an online survey replaced the word ‘yes’ with ‘forks’
Dating back to at least early 2023, a bizarre and alarming technical glitch started popping up in some organizations’ online surveys and forms.
49427
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 12/11/2024
Thanks Elliott. These both appear to be bespoke mail push to web (and phone option, for Franklin and Marshall). Although Dartmouth reinterviewed people from an early Oct survey, neither is a typical prob panel. Plus, F&M's LV estimate was Trump +1 (election result Trump+2), their RV was Harris +4.
000
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 12/11/2024
I'm puzzled by that last line. I assumed that "online prob panel" (bias = 2.8 D) is the line for most of the probability panels used in this cycle. I'm also unaware of errors from any probability panels that were as large as 13 points. @gelliottmorris.bsky.social help us out here!
110
Reposted by Pollcat, AKA Scott Keeter
John Gramlich @johngramlich.bsky.social · 28/08/2024
Our new explainer looks at the key things Americans should know about election polling this year: www.pewresearch.org/short-reads/... One key point: While polling methods have diversified greatly in recent years, not all methods are equally sound. Caveat emptor.
Area chart showing that the number of public pollsters in the United States has increased greatly in recent decades and that survey methods have become more diverse during that span.
134
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 28/08/2024
We put together a little grab-bag of things to know about election polling in the US, for example that polling methods are quite different today than in 2016, that the margin of sampling error captures just one of several kinds of error, and much more pewrsr.ch/3iay5d5
pewrsr.ch
Key things to know about election polling in the United States
The real environment in which polls are conducted bears little resemblance to the idealized settings presented in textbooks.
01213
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 14/07/2024
The party ID is from NPORS and can be filtered on registration in the survey, while the registration parameter itself comes from the CPS
000
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 09/07/2024
Now available from Pew Research Center: the annual National Public Opinion Reference Survey (NPORS), which interviewed 5,626 U.S. adults identified via address-based sampling with a 32% response rate. View key estimates and download the data: pewrsr.ch/3ukleLR
pewrsr.ch
National Public Opinion Reference Survey (NPORS)
NPORS is an annual survey of U.S. adults conducted by the Pew Research Center used to to produce benchmark estimates for several topics.
0134
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 09/07/2024
it's not a slam dunk decision, but we think it's better to use a presidential year estimate than a more recent off-year estimate
110
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 03/07/2024
And of course there is a quiz www.pewresearch.org/methods/quiz...
pewresearch.org
Quiz: Test your polling knowledge
Test your knowledge of public opinion polling by taking our 10-question quiz.
000
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 03/07/2024
This week we released a new version of our short course “Public Opinion Polling Basics.” In six short lessons, I discuss why we have polls, how polls work, the challenges facing polls, what to look for in a poll, and more. A new lesson focuses on election polling. www.pewresearch.org/course/publi...
pewresearch.org
Public Opinion Polling Basics
How do polls work? What are the different kinds of polls? And what should you look for in a high-quality opinion poll? A Pew Research Center survey methodologist answers these questions and more in si...
11111
Reposted by Pollcat, AKA Scott Keeter
John Gramlich @johngramlich.bsky.social · 26/03/2024
"The majority of abortions in the U.S. now involve pills, according to both the CDC and Guttmacher. The CDC says 56% of U.S. abortions in 2021 involved pills, up from 53% in 2020 and 44% in 2019."
pewresearch.org
What the data says about abortion in the U.S.
The U.S. abortion rate has generally declined since the 1980s, but there have been slight upticks in the late 2010s and early 2020s.
022
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 21/03/2024
There is a "Worm Moon" coming on March 25, so I suppose there is also a....
110
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 21/03/2024
Relatively few Americans (22%) say they are closely following news about the Israel-Hamas war, and only about half can correctly report that more Palestinians than Israelis have died since the war’s start. On many attitude questions about the war, sizable numbers express no opinion
022
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 21/03/2024
We just released a new report exploring views of Americans about the Israel-Hamas war, including views among Jewish and Muslim Americans. Despite sharp disagreement on many questions, a majority of the public (57%) expresses sympathy for both the Palestinian and Israeli people pewrsr.ch/4co9bUo
pewrsr.ch
Majority in U.S. Say Israel Has Valid Reasons for Fighting; Fewer Say the Same About Hamas
57% of Americans express some sympathy with both Israelis and Palestinians, including 26% who say their sympathies lie equally with both groups.
296
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 05/03/2024
We just released a new analysis about the potential for opt-in surveys -- those where people volunteer to take surveys -- to provide misleading results, especially for young adults and Hispanics pewrsr.ch/49BMhqF
pewrsr.ch
Online opt-in polls can produce misleading results, especially for young people and Hispanic adults
We examine how an opt-in poll may have unintentionally misled the public about the sensitive issue of Holocaust denial among young Americans.
22227
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 12/02/2024
We look at measures of religious affiliation, family income, political party affiliation, gender identity and sexual orientation, race and ethnicity, and age and generation. Many of these measures have evolved over time in response to growing diversity and changing attitudes among the U.S. public.
000
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 12/02/2024
To help describe the richness of public opinion, pollsters sort people into groups based on their religion, race, gender, partisanship and more. We've written a new data essay that takes a look at the stories behind those measures www.pewresearch.org/methods/2024...
pewresearch.org
Who Are You? The Art and Science of Measuring Identity
As a shop that studies human behavior through surveys and other social scientific techniques, we have a good line of sight into the contradictory nature of human preferences. Here's a look at how we c...
100
Reposted by Pollcat, AKA Scott Keeter
Jens Manuel Krogstad @jensmanuel.bsky.social · 09/01/2024
Last year, my colleagues talked to a group of people who, while they may vote, are not strongly attached to either political party. By and large, they look at the nation’s politics as a topic better avoided than embraced. Here’s what some of them had to say: www.pewresearch.org/politics/?p=...
pewresearch.org
Tuning Out: Americans on the Edge of Politics
Untethered from partisan politics and uninterested in keeping up with political news, here is how some Americans view the current state of U.S. politics.
021
Reposted by Pollcat, AKA Scott Keeter
John Gramlich @johngramlich.bsky.social · 11/12/2023
NEW from the Pew Research Center: Striking findings from 2023 These findings and charts from the past year include a record-high share of unmarried Americans, record-low views of the Supreme Court, rising public concern about artificial intelligence, and more. Read the full list: pewrsr.ch/47PSOx4
Featured image for Pew Research Center's annual list of striking findings from the past year
012
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 28/11/2023
Looking for some non-political content to give your nerves a break? Visit the little village of Tipping Point USA to compare your tipping habits with those of a representative sample of U.S. adults www.pewresearch.org/2023/11/28/d...
pewresearch.org
Do You Tip More or Less Often Than the Average American?
Compare your tipping habits with those of the overall public by visiting Tipping Point, the small town with a big-city feel.
011
Pollcat, AKA Scott Keeter @pollcat.bsky.social · 03/10/2023
Pew Research Center has just released estimates and data from its annual National Public Opinion Reference Survey (NPORS), which interviewed 5,733 U.S. adults identified via address-based sampling. The study had a 31% response rate. View the estimates and download the raw data: pewrsr.ch/3LKNIJC
041