CNN's Polling Analyst's take on the Change Research Poll

[Skya Rhen]

Link to tweet

[OhZone]

1. Ha

Maybe they're researching a way to change things. In a negative sense.

[highplainsdem]

2. K&R. The replies there are also worth reading.

[Cha]

8. Thanks for mentioning the replies,

[bluewater]

3. Unskew the Polls !1!!

It's simply inconceivable that the primary electorate in a given state could be volatile!

Didn't Biden's numbers drop 10% NATIONALLY after the first debate almost over night? Across SEVERAL polls?

Oh... yes they did.

Honestly, unskewing the polls is not a good look.

The polls are what the polls are.

[SouthernProgressive]

5. Your comments here make is clear you have almost no understanding of statistics and polling.

"Honestly, unskewing the polls is not a good look. "

Recognizing red flags and obvious issues is a very good thing. What you call "unskewing" is actually critical thinking.

[bluewater]

6. 538 rates HarrisX and Change Research the same C+ Rating.

Pardon me if I trust 538's abilities more.



Unskewing the polls... not a good look.

[SouthernProgressive]

7. Should give you even more reason for pause, not less.

You again highlight your inability to critically analyze statistics.

"Pardon me if I trust 538's abilities more. "

538 has nothing to do with the poll. You shouldn't blindly trust like that. I also don't know why you think a C+ means unquestionable. That is just flat out strange.

Teacher: You get a C+

Bluewater: Look mom, I got every single question right.

There are some issues with logic here.

[bluewater]

9. Have you never heard of 538 Pollster Ratings?

538 rates HarrisX and Change Research the same C+ rating.

https://projects.fivethirtyeight.com/pollster-ratings/


So, yes, I have faith in 538's opinions about polling firms'relative merits.

Many, many people do.

In September 2014, Silver put into the public domain all of his pollster ratings,[538 42] as well as descriptive summary data for all of the more than 6,600 polls in his data collection for the final three weeks of U.S. Presidential primaries and general elections, state governor elections, and U.S. Senate and U.S. Congress elections for the years 1998–2012.[32] In addition to updating his pollster ratings, he published an updated methodological report.[538 43]

If you have anything substantial to counter 538's ratings, please feel free to present it.

Here is a brief list of some of 538's awards:

In September 2008, FiveThirtyEight became the first blog ever selected as a Notable Narrative by the Nieman Foundation for Journalism at Harvard University. According to the Foundation, "In his posts, former economic analyst and baseball-stats wunderkind Nate Silver explains the presidential race, using the dramatic tension inherent in the run-up to Election Day to drive his narrative. Come November 5, we will have a winner and a loser, but in the meantime, Silver spins his story from the myriad polls that confound us lesser mortals".[73]
The New York Times described FiveThirtyEight in November 2008 as "one of the breakout online stars of the year".[15]

Huffington Post columnist Jason Linkins named FiveThirtyEight as No. 1 of "Ten Things that Managed to Not Suck in 2008, Media Edition".[74]

FiveThirtyEight is the 2008 Weblog Award Winner for "Best Political Coverage".[75]

FiveThirtyEight earned a 2009 "Bloggie" as the "Best Weblog about Politics" in the 9th Annual Weblog Awards.[76]
In April 2009, Silver was named "Blogger of the Year" in the 6th Annual Opinion Awards of The Week, for his work on FiveThirtyEight.[77]

In September 2009, FiveThirtyEight's predictive model was featured as the cover story in STATS: The Magazine for Students of Statistics.[21]

In November 2009, FiveThirtyEight was named one of "Our Favorite Blogs of 2009" ("Fifty blogs we just can't get enough of&quot by PC Magazine.[78]

In December 2009, FiveThirtyEight was recognized by The New York Times Magazine in its "Ninth Annual Year in Ideas" for conducting "Forensic Polling Analysis" detective work on the possible falsification of polling data by a major polling firm.[79][e]

In November 2010, Editor-in-Chief of Politico John F. Harris, writing in Forbes magazine, listed Silver as one of seven bloggers among "The Most Powerful People on Earth".[81]

In June 2011, Time's "The Best Blogs of 2011" named FiveThirtyEight one of its Essential Blogs.[82]

May 2012: FiveThirtyEight won a Webby Award for "Best Political Blog" from the International Academy of Digital Arts and Sciences in the 16th annual Webby Awards.[83]

April 2013: FiveThirtyEight won a Webby Award for "Best Political Blog" from the International Academy of Digital Arts and Sciences in the 17th annual Webby Awards.[84]

June 2016: FiveThirtyEight was named the "Data Journalism Website of the Year" for 2016 by the Global Editors Network, a Paris-based organization that promotes innovation in newsrooms around the world. FiveThirtyEight won an additional award for "News Data App of the Year (large newsroom)" for "Swing the Election," an interactive project by Aaron Bycoffe and David Wasserman.[85]

September 2017: The National Academies of Sciences, Engineering, and Medicine awarded a 2017 Communication Award in the "Online" category to "FiveThirtyEight's Maggie Koerth-Baker, Ben Casselman, Anna Maria Barry-Jester, and Carl Bialik for "Gun Deaths in America." "A balanced and fact-filled examination of an unfolding crisis, with compelling interactives that are meticulously attentive to data quality and statistics."[86]

June 2018: "The Atlas of Redistricting" was named "News App of the Year" by the Data Journalism Awards sponsored by the Global Editors Network. The award summary stated: "The wonky art of drawing U.S. Congressional boundaries can make or break political careers and shape the direction of national lawmaking for a decade. This hands-on app, the centerpiece of FiveThirtyEight's Gerrymandering Project, lets users explore in depth at least seven different remapping goals, from highly partisan favoring one side or the other to maximizing majority-minority districts to creation of districts as compact as possible. The result makes clear the stakes in the looming battles over how new maps will be drawn from 2020 Census data."[87] The Atlas was created by Aaron Bycoffe, Ella Koeze, David Wasserman, and Julia Wolfe.

Again, If you have anything substantial to counter 538's ratings, please feel free to present it.

[SouthernProgressive]

10. I'm extremely well aware of Nate and 538.

Your post here has very little to do with what we are discussing.

You keep mentioning HarrisX yet I don't see where they are any part of the op or conversation.

Each post of mine stands on solid ground.

I have no clue why you think C+ at 538 means infallible. 538 doesn't agree with you. No one would.

[bluewater]

12. Harris and Change Research STILL both have the same C+ rating by 538

Sorry, but that is a fact.

Harris and Change Research STILL both have the same C+ rating by 538.

Facts are stubborn things.

[SouthernProgressive]

13. I would call your tact more of a deflection than a strawman.

"Sorry, but Harris and Change Research STILL both have the same C+ rating by 538. "

Where is Harris mentioned anywhere in the op?

What does 538 giving Change a C+ rating have anything to do with your passionate argument that the poll is infallible?

Nate and 538 are in complete disagreement with you on that one. He believes polls should be questioned. You are opposed to everything 538 stands for yet keep using them to deflect.

"Sorry, but Harris and Change Research STILL both have the same C+ rating by 538 and bluewater thinks that means they are unquestionable."

That is a fact as you have outlined in our conversation. Facts are stubborn little things.

I get that not questioning polls is your thing. I get that not analyzing statistics is your thing. I get that saying C+ over and over again makes you feel comfortable that there is nothing to question. It's not a good look.

You have also incorrectly used the concept of a "strawman" argument. That one is a lot more simple to understand than statistics.

[bluewater]

14. So it's back to UNSKEW the POLLS !!!111!!!!!1! ?

Not a good look.



lets all denigrate Change Research because we don't like its results, but lets all love Harris because we DO like its results

Even though highly respected polling experts at 538 rate BOTH polling firms the same C+ rating.

Got it.

Thanks for the Discussion!

If you ever find anything substantial to counter 538's ratings, please post it. Till then, best regards!

[SouthernProgressive]

15. No clue why you keep mentioning Harris.

They aren't in the op anywhere.

"lets all denigrate Change Research because we don't like its results, but lets all love Harris because we DO like its results " <- This is a strawman.

I have not denigrated Change or loved Harris. I don't even get what you are talking about. I've done neither and Harris isn't any part of the op.

"If you ever find anything substantial to counter 538's ratings, please post it. Till then, best regards!" <- This is an actual strawman.

Why would I want to counter 538's C+ rating of Change? I haven't attempted to do so.

Nate disagrees with you. He doesn't believe the poll is infallible as you do. You should probably stop using 538 as you are. Nate is opposed to the position you are taking.

Please not the two above stawman arguments you have put forward are truly strawman arguments. Unlike what you accused me of above which is not a strawman.

[bluewater]

16. "He doesn't believe the poll is infallible as you do." Classic strawman/ad hominem attack

Please cut and paste where I said "the poll is infallible".

That should be simple, right?

Anything CLOSE to me saying the poll is INFALLIBLE will suffice.

Please, substantiate your claim, otherwise it remains a strawman / ad hominem attack without merit.

[SouthernProgressive]

17. You have repeatedly stated that polls are not to be "unskewed."

Again, you have improperly used the concept of a strawman. That is twice now. Please see my posts above where I highlight your actual strawman arguments.

I was completely correct. Nate completely disagrees with you that polls shouldn't be analyzed, or "unskewed" as you like to call it.

Emoticons aren't distracting from your flawed argument.

If these polls are not infallible, why in the world would you want people to not analyze them? You are actually passionate about it.

Not wanting people to analyze statistics presented by groups with a C+ by 538 is actually an anti-scientific position to hold.

[bluewater]

19. lol So nothing?

No quotes of me saying the "poll is infallible"?

Nothing even close?



hey, thanks for the discussion!

It's been fun.

[SouthernProgressive]

20. I did highlight it.

Emoticons won't distract from the words you have used.

[Thekaspervote]

22. How true!

[Tarheel_Dem]

23. +10000

[bluewater]

24. "Unskewing the polls" is a half baked attempt to question the results of professional posters.

"Unskewing the polls" is a half baked attempt to question the results of professional posters. It's been a meme at least since 2012.

Here is an article that serves as a good refresher course for what "unskewing" polls means:

No, You May Not “Unskew” My Polls: A Refresher
by: Julia Clark | Elections, Public Affairs, Public Opinion | Oct 7, 2016

It seems that I need to re-up my 2012 post on “why having unequal numbers of Democrats and Republicans in polls is OK”. I was hoping after the massive failure of the “Unskewing Guy” in 2012 I wouldn’t have to revisit this, but it seems I’m wrong. If the amount of abusive emails and tweets we get accusing us of intentionally biasing the polls is any indicator, even MORE people this year feel compelled to attempt to “unskew” the polls than they did in 2012.

I’m going to be a bit impolitic up front and admit that I have no time for this nonsense. Anyone with a working understanding of the American electorate and how polling functions comprehends why polls of the population of 18+ Americans do NOT (and should not) contain equal numbers of Democrats and Republicans. I find amateur attempts to slander the polls on the basis of this issue infuriating and unworthy of notice or response. But I am going to sit here and re-write this blog in the hopes that at the very least it reduces the volume of hate mail we get…

Ipsos has been getting a lot of questions lately about the political makeup of polls. This is normal towards the end of an election cycle – lots of people scrutinize the polls a lot more closely! In an effort to explain this clearly, we first need to make some distinctions between question types. My colleague Chris has already explained the difference between all voting age Americans, Registered Voters, and Likely Voters. Equally important in political polling is being clear about the different types of questions we use to look at the political balance of our samples. We’ve covered the basic ones below:

https://spotlight.ipsos-na.com/public-affairs/no-you-may-not-unskew-my-polls-a-refresher/

So, once again, Unskewing the polls is not a good look.



So, your strawman / ad hominem attack that I said "the poll is infallible" aside, it's been fun chatting.

It really has.

[SouthernProgressive]

26. Your link is another deflection that adds nothing.

It’s a copy and paste job of something that is irrelevant followed by emoticons.

Once again, that is a strawman argument you are presenting. You keep referring to that term and clearly don’t know what it means.

You have yet again shown your intense desire for no one to question polls.

[Thekaspervote]

21. Agree with you southernprogressive!!

Seems somebody has their knickers in a twist.

[BannonsLiver]

27. +1000000

The phony happy warrior schtick and self assured armchair political pollster expert routine have become tiresome.

[Tarheel_Dem]

4. I'm surprised anyone still posts, or believes, Change Research results. n/t

[crazytown]

18. What on earth do you mean :)

[Demsrule86]

25. They are an any poll result you want, we promise kind of poll...

Not legit and all over the place.

[NYMinute]

11. Change Research

"We'll give you any result you want from our polls!"