Raphael Nishimura
@rnishimura.bsky.social
Survey methodologist and statistician at the Survey Research Center, Institute for Social Research, University of Michigan
#survey | #sampling | #statistics | #RStats
#survey | #sampling | #statistics | #RStats
For reference, it took Selzer 12 days after the election last year to produce and release a full post-mortem of her infamous poll.
Given their background on methodological transparency, I'd be very surprise if we see anything remotely similar from this so-called "America's most accurate pollster".
Given their background on methodological transparency, I'd be very surprise if we see anything remotely similar from this so-called "America's most accurate pollster".
AtlasIntel, the self-proclaimed “best pollster in America,” missed last week’s elections by an average of 9 points across races and by 14 points in New Jersey.
Back in June, I wrote about how their accuracy in 2024 distracted from bigger methods issues: www.gelliottmorris.com/p/the-best-p...
Back in June, I wrote about how their accuracy in 2024 distracted from bigger methods issues: www.gelliottmorris.com/p/the-best-p...
What makes the “best pollsters” of 2024 so accurate?
Primarily it’s a mix of experimentation and biased estimates that get lucky
www.gelliottmorris.com
November 10, 2025 at 3:09 PM
For reference, it took Selzer 12 days after the election last year to produce and release a full post-mortem of her infamous poll.
Given their background on methodological transparency, I'd be very surprise if we see anything remotely similar from this so-called "America's most accurate pollster".
Given their background on methodological transparency, I'd be very surprise if we see anything remotely similar from this so-called "America's most accurate pollster".
Did you say "representative sample"?
November 7, 2025 at 11:44 PM
Did you say "representative sample"?
A year ago today, AtlasIntel said they would deposit at the Roper Center the raw data from their final polls. It's still not there.
Something tells me they will not be depositing that data file, neither the ones from this week's polls...
Something tells me they will not be depositing that data file, neither the ones from this week's polls...
November 7, 2025 at 8:47 PM
A year ago today, AtlasIntel said they would deposit at the Roper Center the raw data from their final polls. It's still not there.
Something tells me they will not be depositing that data file, neither the ones from this week's polls...
Something tells me they will not be depositing that data file, neither the ones from this week's polls...
I was just saying this in the other site: Mamdani's share should probably have a heavier weight in the post-election polling analysis than Cuomo's share, or at least it should be put together with Sliwa's, given the likely late shift.
And looks like somebody already did it.
And looks like somebody already did it.
November 6, 2025 at 6:14 PM
I was just saying this in the other site: Mamdani's share should probably have a heavier weight in the post-election polling analysis than Cuomo's share, or at least it should be put together with Sliwa's, given the likely late shift.
And looks like somebody already did it.
And looks like somebody already did it.
Believe or not, the New Jersey poll wasn't the lowest point in US elections for the (former?) "American most accurate pollster", AtlasIntel
Take a look at their final poll in the PNP Primaries in Puerto Rico last year:
Poll: Pierluisi +14
Result: González +9
That's a 23-points difference!
Take a look at their final poll in the PNP Primaries in Puerto Rico last year:
Poll: Pierluisi +14
Result: González +9
That's a 23-points difference!
November 6, 2025 at 3:05 AM
Believe or not, the New Jersey poll wasn't the lowest point in US elections for the (former?) "American most accurate pollster", AtlasIntel
Take a look at their final poll in the PNP Primaries in Puerto Rico last year:
Poll: Pierluisi +14
Result: González +9
That's a 23-points difference!
Take a look at their final poll in the PNP Primaries in Puerto Rico last year:
Poll: Pierluisi +14
Result: González +9
That's a 23-points difference!
l guess NJ is a small demographic subgroup for AtlasIntel standards?
November 5, 2025 at 5:06 AM
l guess NJ is a small demographic subgroup for AtlasIntel standards?
Mood da noite
November 5, 2025 at 3:01 AM
Mood da noite
Also, can we all put to bed now the myth of "the most accurate pollster in the US"?
I know I've been saying this since after the 2020 election, but I think we can finally agree on that, right?! RIGHT?!?
I know I've been saying this since after the 2020 election, but I think we can finally agree on that, right?! RIGHT?!?
November 5, 2025 at 2:35 AM
Also, can we all put to bed now the myth of "the most accurate pollster in the US"?
I know I've been saying this since after the 2020 election, but I think we can finally agree on that, right?! RIGHT?!?
I know I've been saying this since after the 2020 election, but I think we can finally agree on that, right?! RIGHT?!?
Wow, turns out weighting the hell out of your sample recruited through river sampling out of ads in social media doesn't work after all, who knew?! 🤭
November 5, 2025 at 2:31 AM
Wow, turns out weighting the hell out of your sample recruited through river sampling out of ads in social media doesn't work after all, who knew?! 🤭
I've been calling AtlasIntel's poor (to say the least) methodology out since after the 2020 elections, when it was not a popular thing to say. I'm just glad you all caught up and we are all on the same page now!
be careful with pollsters who invest a lot of time and money into marketing based off single election performance, and don't appear to take methods too seriously
www.gelliottmorris.com/p/the-best-p...
www.gelliottmorris.com/p/the-best-p...
November 5, 2025 at 2:10 AM
I've been calling AtlasIntel's poor (to say the least) methodology out since after the 2020 elections, when it was not a popular thing to say. I'm just glad you all caught up and we are all on the same page now!
Reposted by Raphael Nishimura
ANES Data Release! electionstudies.org/data-center/...
The 3-wave ANES panel is now available. It merges data from 3 election studies (2016-2020-2024), the first time the ANES has collected interviews of the same respondents across 3 presidential elections.
The 3-wave ANES panel is now available. It merges data from 3 election studies (2016-2020-2024), the first time the ANES has collected interviews of the same respondents across 3 presidential elections.
2016-2020-2024-panel-merged-study - ANES | American National Election Studies
electionstudies.org
November 1, 2025 at 8:47 PM
ANES Data Release! electionstudies.org/data-center/...
The 3-wave ANES panel is now available. It merges data from 3 election studies (2016-2020-2024), the first time the ANES has collected interviews of the same respondents across 3 presidential elections.
The 3-wave ANES panel is now available. It merges data from 3 election studies (2016-2020-2024), the first time the ANES has collected interviews of the same respondents across 3 presidential elections.
They literally just published a NYC poll two days ago, but sure, why not?
November 3, 2025 at 4:11 AM
They literally just published a NYC poll two days ago, but sure, why not?
LMAO That's not how margins of error work. They reflect random sampling error (variance), not systematic errors, which clearly seems to be the case here, when looking across polls.
Also, saying with a straight face that what's shady is if the crosstab looks okay. C'mon, you are not even trying! 😅
Also, saying with a straight face that what's shady is if the crosstab looks okay. C'mon, you are not even trying! 😅
November 3, 2025 at 1:40 AM
LMAO That's not how margins of error work. They reflect random sampling error (variance), not systematic errors, which clearly seems to be the case here, when looking across polls.
Also, saying with a straight face that what's shady is if the crosstab looks okay. C'mon, you are not even trying! 😅
Also, saying with a straight face that what's shady is if the crosstab looks okay. C'mon, you are not even trying! 😅
🚨It's finally here!🚨
AAPOR's Taskforce on 2024 Pre-Election Polling report is out!
Full report: /https://aapor.org/wp-content/uploads/2025/10/AAPOR-Task-Force-on-2024-Pre-Election-Polling_Report.pdf
Executive summary: aapor.org/wp-content/u...
AAPOR's Taskforce on 2024 Pre-Election Polling report is out!
Full report: /https://aapor.org/wp-content/uploads/2025/10/AAPOR-Task-Force-on-2024-Pre-Election-Polling_Report.pdf
Executive summary: aapor.org/wp-content/u...
aapor.org
October 29, 2025 at 5:12 PM
🚨It's finally here!🚨
AAPOR's Taskforce on 2024 Pre-Election Polling report is out!
Full report: /https://aapor.org/wp-content/uploads/2025/10/AAPOR-Task-Force-on-2024-Pre-Election-Polling_Report.pdf
Executive summary: aapor.org/wp-content/u...
AAPOR's Taskforce on 2024 Pre-Election Polling report is out!
Full report: /https://aapor.org/wp-content/uploads/2025/10/AAPOR-Task-Force-on-2024-Pre-Election-Polling_Report.pdf
Executive summary: aapor.org/wp-content/u...
I don't know who else still needs to hear this, but raking is not post-stratification. Could you all just stop using "post-stratification" as a synonym for "raking", or more generally, "calibration"?
October 28, 2025 at 5:22 PM
I don't know who else still needs to hear this, but raking is not post-stratification. Could you all just stop using "post-stratification" as a synonym for "raking", or more generally, "calibration"?
I'm a sampling statistician and a lot of people ask me about "representative samples". Since there is quite some confusion about it, I'm putting here an entire thread with everything you need to know about "representative samples": 🧵 [1/n]
October 22, 2025 at 2:32 PM
I'm a sampling statistician and a lot of people ask me about "representative samples". Since there is quite some confusion about it, I'm putting here an entire thread with everything you need to know about "representative samples": 🧵 [1/n]
Happy World Statistics Day! 🎉📊🤓
Statistics plays a fundamental role in helping us describe and better understand our world through high-quality data.
#WorldStatisticsDay
Statistics plays a fundamental role in helping us describe and better understand our world through high-quality data.
#WorldStatisticsDay
October 20, 2025 at 3:09 PM
Happy World Statistics Day! 🎉📊🤓
Statistics plays a fundamental role in helping us describe and better understand our world through high-quality data.
#WorldStatisticsDay
Statistics plays a fundamental role in helping us describe and better understand our world through high-quality data.
#WorldStatisticsDay
Reposted by Raphael Nishimura
new polls website just dropped fiftyplusone.news
October 9, 2025 at 2:49 PM
new polls website just dropped fiftyplusone.news
Oh, I see some new weighting variables here. Cool!
And yes, the methods report is the very first thing I look at a new poll 🤓
And yes, the methods report is the very first thing I look at a new poll 🤓
September 30, 2025 at 3:11 PM
Oh, I see some new weighting variables here. Cool!
And yes, the methods report is the very first thing I look at a new poll 🤓
And yes, the methods report is the very first thing I look at a new poll 🤓
Interesting result on the effect of presenting a "No opinion" option on this Washington Post-Ipsos poll
www.washingtonpost.com/politics/202...
www.washingtonpost.com/politics/202...
September 19, 2025 at 1:46 PM
Interesting result on the effect of presenting a "No opinion" option on this Washington Post-Ipsos poll
www.washingtonpost.com/politics/202...
www.washingtonpost.com/politics/202...
Reposted by Raphael Nishimura
Dr. Sunghee Lee (@sungheelee.bsky.social) featured in this NYT article examining the consequences of deep NIH cuts on health disparities research. Her work on dementia in underrepresented populations was defunded despite its critical value.
Read more: myumi.ch/W6dZb
#HealthEquity #SocialResearch
Read more: myumi.ch/W6dZb
#HealthEquity #SocialResearch
August 13, 2025 at 3:13 PM
Dr. Sunghee Lee (@sungheelee.bsky.social) featured in this NYT article examining the consequences of deep NIH cuts on health disparities research. Her work on dementia in underrepresented populations was defunded despite its critical value.
Read more: myumi.ch/W6dZb
#HealthEquity #SocialResearch
Read more: myumi.ch/W6dZb
#HealthEquity #SocialResearch
Reposted by Raphael Nishimura
I got asked to take uncertainty intervals off a chart because the lower tail showed potentially a 0% lift and like nah dawg I will not be doing that. You can take uncertainty out of the chart but you can't take it out of the system --- if you wanna delude yourself, that's between you and god
August 7, 2025 at 2:00 PM
I got asked to take uncertainty intervals off a chart because the lower tail showed potentially a 0% lift and like nah dawg I will not be doing that. You can take uncertainty out of the chart but you can't take it out of the system --- if you wanna delude yourself, that's between you and god
🚨 All data nerds 🤓: ANES 2024 full release is now available!
The full release of the ANES 2024 Time Series #Data is now available. More details here: electionstudies.org/anes-announc...
August 12, 2025 at 5:51 PM
🚨 All data nerds 🤓: ANES 2024 full release is now available!
🚨 For all data nerds 🤓 out there: incoming announcement for a new data release!
August 11, 2025 at 5:30 PM
🚨 For all data nerds 🤓 out there: incoming announcement for a new data release!
Reposted by Raphael Nishimura
THREAD: There are a lot of unanswered questions 12 hours after President Trump — who, according to the Constitution, has no final authority over the census — released a social media post calling for unprecedented changes to how the government produces data that forms the foundation of U.S. democracy
Trump wants a new U.S. census to exclude people here illegally. It'd be unprecedented
Trump is calling for a "new" census that excludes people in the U.S. without legal status. The 14th Amendment requires the "whole number of persons in each state" in a key set of census results.
www.npr.org
August 7, 2025 at 11:22 PM
THREAD: There are a lot of unanswered questions 12 hours after President Trump — who, according to the Constitution, has no final authority over the census — released a social media post calling for unprecedented changes to how the government produces data that forms the foundation of U.S. democracy