Overtime Politics Thread (WARNING: Possible fraud)

[Ebsy]

I've met obnoxious Hillary supporters and obnoxious Bernie supporters. However, Atlas has many, many more obnoxious Hillary supporters than obnoxious Bernie supporters.

Could you provide a list of both so we can quantify how many is "many more?"

You for starters with your obvious hackishness.

Thanks hon.

[Fmr President & Senator Polnut]

It seems as though the Republican polls on here are pretty normal but the democratic numbers are insane....hmmm...I would however like to get another polling organization to agree. If the Republican nominee is Trump there no question Hillary would perform less then Sanders. The only thing trump has in his back pocket is anti-establishment and if Hillary is the nominee he will use that. What can he even use on Sanders that he's a socialist? He's a clown and people would probably rather vote for Bernie.

Its relatively straight-forward to me. The issue is putting this lot aside, Trump is the leader in the GOP race because he probably over-performs in the Internet-based polling. Sanders is in the same boat, he performs best in that kind of polling, so it generates potentially more outliers.

But the point isn't trying to find a polling narrative that helps the candidate you prefer, polling dynamics will shift continually over the next months, which is why GE match-ups are pointless. Unless they're in an early state most people haven't engaged.

[Crumpets]

It seems as though the Republican polls on here are pretty normal but the democratic numbers are insane....hmmm...I would however like to get another polling organization to agree. If the Republican nominee is Trump there no question Hillary would perform less then Sanders. The only thing trump has in his back pocket is anti-establishment and if Hillary is the nominee he will use that. What can he even use on Sanders that he's a socialist? He's a clown and people would probably rather vote for Bernie.

I think Overtime Politics might be oversampling whites and possibly the young as well. For the Republican primary, that wouldn't have much of an impact, but for Democrats, it would definitely favor Sanders. The Democratic numbers do look reasonable in for the younger-white demographic.

[Mr. Morden]

Sorry, I realize this is explained earlier in the thread, but can someone remind me: Have they said that they're going to start actually *weighting* by demographics, or just asking demographic questions, but leaving the topline #s unweighted?

[The Other Castro]

Sorry, I realize this is explained earlier in the thread, but can someone remind me: Have they said that they're going to start actually *weighting* by demographics, or just asking demographic questions, but leaving the topline #s unweighted?

I believe they will just be asking the demographic information and using that to provide breakdowns to the responses already received. According to their post, "We have decided to add age, gender, income, and ethnicity to our polling script, and we will be breaking down support based on those groups."

[○∙◄☻¥tπ[╪AV┼cVê└]

Sorry, I realize this is explained earlier in the thread, but can someone remind me: Have they said that they're going to start actually *weighting* by demographics, or just asking demographic questions, but leaving the topline #s unweighted?

I believe they will just be asking the demographic information and using that to provide breakdowns to the responses already received. According to their post, "We have decided to add age, gender, income, and ethnicity to our polling script, and we will be breaking down support based on those groups."

Of course you can always personally "unskew" them.

[Fmr President & Senator Polnut]

Sorry, I realize this is explained earlier in the thread, but can someone remind me: Have they said that they're going to start actually *weighting* by demographics, or just asking demographic questions, but leaving the topline #s unweighted?

I don't think this lot is actually capable of scientific polling.

[○∙◄☻¥tπ[╪AV┼cVê└]

Just saying that if I was to make up fake poll results to make Bernie look good, I would give Hillary more than a 5 point lead in Missouri and Arkansas.

[mds32]

Michigan Democratic Primary
Dec. 31st

Hillary Clinton- 191 – 47%
Bernie Sanders – 163 – 40%
Martin O’Malley – 10 – 2%
Undecided – 41 – 10%

[Eraserhead]

Michigan Democratic Primary
Dec. 31st

Hillary Clinton- 191 – 47%
Bernie Sanders – 163 – 40%
Martin O’Malley – 10 – 2%
Undecided – 41 – 10%

Are they calling any black folks?

[Attorney General & PPT Dwarven Dragon]

http://overtimepolitics.com/pollingdata/OvertimePolitics.comDec31-Jan3DemocraticPrimaryPoll-Michigan.pdf

[Ebsy]

Complete junk.

[Attorney General & PPT Dwarven Dragon]

These demographic numbers don't exactly vouch for these polls being accurate:

Vote by Race:

White: Sanders 43/41
Black: Clinton 63/31 (?!?!?!?)
Latino: Clinton 48/40 (HUH?)
Asian: Clinton 45/44 (WTF?)
Other: Clinton 44/42

Vote by Age:

18-30: 47-39 Sanders
31-45: 49-36 Clinton
46-59: 47-41 Clinton ()
60+: 48-44 Clinton (WTF???)

Gender at least seems okay - Clinton is ahead 43/42 with Men, 52/37 with Women

[Lief 🗽]

lol what is the point of demographic breakdowns if they don't tell us the demographic composition of their sample??

[○∙◄☻¥tπ[╪AV┼cVê└]

These demographic numbers don't exactly vouch for these polls being accurate:

Vote by Race:

White: Sanders 43/41
Black: Clinton 63/31 (?!?!?!?)
Latino: Clinton 48/40 (HUH?)
Asian: Clinton 45/44 (WTF?)
Other: Clinton 44/42

Vote by Age:

18-30: 47-39 Sanders
31-45: 49-36 Clinton
46-59: 47-41 Clinton ()
60+: 48-44 Clinton (WTF???)

Gender at least seems okay - Clinton is ahead 43/42 with Men, 52/37 with Women

The MOE on some of those subsamples is going to be large.

lol what is the point of demographic breakdowns if they don't tell us the demographic composition of their sample??

You can at least figure it out for gender. They did overpoll men. Reweighting,  it should be more like 48-39.

[Adam Griffin]

THEY'RE LITERALLY PULLING STUFF OUT OF THEIR ASSES

I'm not sure if anybody else has suggested it thus far, but I've been convinced from the beginning that "they" are really just one person who is literally making figures up, and not actually polling anyone. My suspicions were heightened when it became so easy for them to go from "well we're just a small-time group and we don't have time to ask all of these questions" to "OK we're going to do it".

Now, this Michigan poll...

Supposedly, they sampled 405 people. Now, let's look at the 2012 exit polls. In Michigan, 3% of the voters were non-black, non-white, non-latino voters. Among the Democratic electorate, this group would comprise at most 5% of the electorate, but in a primary...likely less. However, let's just assume that for argument's sake, it's 5%.

In their poll, Asian voters were 45-44; Nat-Am and Other were 44-42. Five percent of 405 people = 20 people. This means at minimum, there should be 5 percentage points' difference between the two candidates in said group if just one person more supported Clinton than Sanders, or vice-versa. However, these are two separate groups, splitting (what should be no more than) five percentage. Let's say the two groups were sampled equally and combined, comprised five percentage. That means that just one more person supporting a given candidate would give you a ten point difference.

Yet in these "crosstabs", there is only a 1-point difference among Asians and a 2-point difference among others. You'd have to have 12% of the poll's respondents be Asian in order to have such a scenario be possible; 24% of the poll's respondents be Nat-Am/Other for the same. Even if you assume "rounding error", you'll still looking at these two groups needing to comprise roughly 25% of the people surveyed.

IT'S BOGUS, MADE-UP BS - PURGE ANY OF THESE FROM THE DATABASE IF THEY EXIST

[○∙◄☻¥tπ[╪AV┼cVê└]

THEY'RE LITERALLY PULLING STUFF OUT OF THEIR ASSES

I'm not sure if anybody else has suggested it thus far, but I've been convinced from the beginning that "they" are really just one person who is literally making figures up, and not actually polling anyone. My suspicions were heightened when it became so easy for them to go from "well we're just a small-time group and we don't have time to ask all of these questions" to "OK we're going to do it".

Now, this Michigan poll...

Supposedly, they sampled 405 people. Now, let's look at the 2012 exit polls. In Michigan, 3% of the voters were non-black, non-white, non-latino voters. Among the Democratic electorate, this group would comprise at most 5% of the electorate, but in a primary...likely less. However, let's just assume that for argument's sake, it's 5%.

In their poll, Asian voters were 45-44; Nat-Am and Other were 44-42. Five percent of 405 people = 20 people. This means at minimum, there should be 5 percentage points' difference between the two candidates in said group if just one person more supported Clinton than Sanders, or vice-versa. However, these are two separate groups, splitting (what should be no more than) five percentage. Let's say the two groups were sampled equally and combined, comprised five percentage. That means that just one more person supporting a given candidate would give you a ten point difference.

Yet in these "crosstabs", there is only a 1-point difference among Asians and a 2-point difference among others. You'd have to have 12% of the poll's respondents be Asian in order to have such a scenario be possible; 24% of the poll's respondents be Nat-Am/Other for the same. Even if you assume "rounding error", you'll still looking at these two groups needing to comprise roughly 25% of the people surveyed.

IT'S BOGUS, MADE-UP BS - PURGE ANY OF THESE FROM THE DATABASE IF THEY EXIST

Because of rounding that 1 point difference could be almost 2 points. The more problematic thing is O'Malley at 1% for both. For that, there had to be at least 67 voters for it to be in [0.5%, 1.5) to round to 1%. 67/405 = 16.5%. So 33% that aren't white, black or hispanic.

[ProgressiveCanadian]

No one on here will ever be happy with this polling orginization if they do not have Hillary leading by 30.

[Fmr President & Senator Polnut]

These demographic numbers don't exactly vouch for these polls being accurate:

Vote by Race:

White: Sanders 43/41
Black: Clinton 63/31 (?!?!?!?)
Latino: Clinton 48/40 (HUH?)
Asian: Clinton 45/44 (WTF?)
Other: Clinton 44/42

Vote by Age:

18-30: 47-39 Sanders
31-45: 49-36 Clinton
46-59: 47-41 Clinton ()
60+: 48-44 Clinton (WTF???)

Gender at least seems okay - Clinton is ahead 43/42 with Men, 52/37 with Women

I knew this lot were garbage... now I know for sure.

[Attorney General & PPT Dwarven Dragon]

For now, I have decided to not include this specific poll, and most future overtime polls, in my map of the polls for the democratic nomination. The demographic breakdowns just do not seem plausible enough, and the Michigan poll currently included in the map did not include Biden or Warren. I will keep the overtime polls that are already in the map in there for now, but will not be adding any more of them unless it is for a state with no previous polls that did not include Warren and/or a significant Biden showing, until I am convinced that this polling company is on to something real with its demographic breakdowns.

[Ebsy]

I think it is obvious to everyone other than noted fools that this firm is bogus.

[Attorney General & PPT Dwarven Dragon]

This delay in the release of the MO republican poll is interesting to say the least. I don't think we've ever had a polling company release a poll literally in the middle of the night, assuming he doesn't hold off until the morning.

[Eraserhead]

No one on here will ever be happy with this polling orginization if they do not have Hillary leading by 30.

Dude, they're fake polls. There's no reason to turn this into a Bernie vs. Hillary thing.

[Attorney General & PPT Dwarven Dragon]

If this guy is actually ambitious enough to be coming up with demographic tables and topline numbers - which include an exact number of people who selected each topline option - completely out of his head, without calling anyone or having any help - essentially just trying to 'read the tea leaves', then a part of me is honestly impressed, especially if he keeps "polls" coming well into 2016 and does eventually provide a quasi-physical address as promised. I'm not quite sure what the motivation would be for creating a long-running "polling company parody", especially since his email is already littered with death threats less than a month into it, but whatever. I honestly think it is more likely that this is real polling, just without demographic weighting, than some random guy literally making up numbers and demographic tables for (potentially) months on end. Once we get to the actual primaries and caucuses, we will have a real answer on exactly how much demographic weighting matters.

[Mr. Morden]

"Donald J. Trump is calling for a total and complete shutdown of Overtime Politics polls entering the US Election Atlas until our forum's representatives can figure out what is going on."