Baseball for the Thinking Fan

Login | Register | Feedback

btf_logo
You are here > Home > Baseball Newsstand > Baseball Primer Newsblog > Discussion
Baseball Primer Newsblog
— The Best News Links from the Baseball Newsstand

Wednesday, October 31, 2012

OTP November 2012 - Moneypoll! The Pundits vs. The Election-Data Nerds

Come next Tuesday night, we’ll get a resolution (let’s hope) to a great ongoing battle of 2012: not just the Presidential election between Barack Obama and Mitt Romney, but the one between the pundits trying to analyze that race with their guts and a new breed of statistics gurus trying to forecast it with data.

In Election 2012 as seen by the pundits–political journalists on the trail, commentators in cable-news studios–the campaign is a jump ball. There’s a slight lead for Mitt Romney in national polls and slight leads for Barack Obama in swing-state polls, and no good way of predicting next Tuesday’s outcome beyond flipping a coin. ...

Bonus link: Esquire - The Enemies of Nate Silver

Joe Kehoskie Posted: October 31, 2012 at 11:42 PM | 11298 comment(s) Login to Bookmark
  Tags: mr president, off-topic, politics, sabermetrics, usa

Reader Comments and Retorts

Go to end of page

Statements posted here are those of our readers and do not represent the BaseballThinkFactory. Names are provided by the poster and are not verified. We ask that posters follow our submission policy. Please report any inappropriate comments.

Page 12 of 114 pages ‹ First  < 7 8 9 10 11 12 13 14 15 16 17 >  Last ›
   1101. Morty Causa Posted: November 03, 2012 at 03:32 PM (#4291871)
I realize it's not the same thing, but BITD half the 8 year olds on my block in DC owned "Daisy / Red Ryder" BB guns that were advertised on the back cover of comic books. They're not deadly or anything, but they can sure put some kid's eye out. They still make them, and I have no idea whether or not gun laws apply to them, but they sure didn't back then.


You city boys need to learn how those in the provinces once lived. In my country town where I grew up and went to school, farms kids not only got shotguns when they learned to walk practically, those who came to school in their pickup trucks had a gun rack over their rear window, which they parked on school grounds. (I don't think they locked the doors either.) And not once in those years did it occur to me, or any other kid, that if you got into a tiff with someone, he was going to go to his truck and get his gun.
   1102. cercopithecus aethiops Posted: November 03, 2012 at 03:32 PM (#4291873)
Exactly. Kings and tyrants have been known to be deposed.


Have you no soul, that you would so flippantly derail a Monty Python hijack?
   1103. tshipman Posted: November 03, 2012 at 03:33 PM (#4291874)
BITD half the 8 year olds on my block in DC owned "Daisy / Red Ryder" BB guns ...they can sure put some kid's eye out


If this was not an intentional reference to A Christmas Story, then it's hilarious.

***

If Wisconsin goes for Romney, then yes, that's a systemic failure of polling. The polling average in Wisconsin is over five points for Obama. That's a huge miss.

My prediction is 332 for Obama, 206 for Romney, and a 50.5-48.5 margin in the popular vote.

***

No one seems to have mentioned this, but the value in Nate's site is setting percentages waaaaaay in advance. All poll aggregators are equal the week before the election. Nate's value comes from showing trends months in advance.
   1104. McCoy Posted: November 03, 2012 at 03:34 PM (#4291875)
I'm too lazy to learn the ins and outs of how the pollsters conduct their surveys and how they adjust and report their results. But it seems like the RCP simple analysis of those polls and Nate's overly complicated (and possibly biased) analysis of those polls are telling us the same thing.

RCP says that Obama will win with a .1 point lead while 538 is predicint an over 2 point win for Obama. A .1 lead would probably be in the mid to high 50's for Obama instead of an 80+% chance of winning that a 2+ point lead predicts.
   1105. Joe Kehoskie Posted: November 03, 2012 at 03:34 PM (#4291876)
Of course, the other point is that it's still an Obama lead, and in line with his lead in most other polls of LV. Including the ones that you say are passing too many of the respondents.

Sure, but it went from being an 8-point Obama lead to something like a 2-point Obama lead at 2008's turnout level. That's well within the margin of error, while Nate is giving Obama ~85 percent odds based on slim leads like that one in Ohio and 1-2 other states.
   1106. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 03:34 PM (#4291877)
Anyhow, I've heard the arguments for the free market plenty of times, I guess. I'm more curious out of morbid fascination than anything else to see if a $30 per gallon price helps anyone or anything in NJ. Not as convinced, obviously.
It does introduce the impossibility for a lot of people of simply filling up the tank.

My heart's with Christie, but my head's with Stossel. It's hard to imagine how anyone would want to transport gas from faraway places to New Jersey if they thought they couldn't make a profit on it, especially considering that under normal circumstances New Jersey's gas prices are usually about the lowest anywhere in the East.
While jacking up the price is simpler, on the surface, I'd prefer a subsidy or payout to suppliers bringing in gas. Spread the pain, which is a useful theory in emergencies, rather than hurt the less able or the poor.

What could happen is a low turnout. Obama still carries both states easily, but his national popular vote total takes a hit, leading to Repub cries of illegitimate.
In other words, you're saying nothing will change?

I wasn't suggesting what we know now about Benghazi should lead to impeachment. But it has been put forward that there was malfeasance and cover-up.


IF - IF - there was, then that is the sort of topic and behavior that I think should be the basis for impeachment. Malfeasance in the duties of president. Not ordinary citizen-like crimes.
If we haven't gotten near a war crimes based impeachment in the decade, though, what on earth would the standard be?

I haven't followed the Nate Silver saga, but what added value does he claim to bring over just looking at the polls themselves?
Nate can edit poll results (as can anyone interested and savvy enough) to make them more accurate; tweak them in ways they need to be tweaked, discount the ones that show bias, and so on. It may be Gallup, for example, that doesn't call cell phones. Adjusting for that in ways that Gallup doesn't is important.

I think it's more likely than not. The polls are likely missing the enthusiasm/turnout gap, many by a substantial margin. The fundamentals are just too unfavorable for Obama.
Don't forget the 'mine-shaft gap'. They're missing that one, too!

He should avoid precise percentages when talking about events that are too infrequent to estimates percentage odds reliably. It's like quantifying a teams chance of winning the World Series in percentages in April, it's stupid. Stick to toss-up, leans-O/R, likely O/R, very-likely O/R.
Spoken like someone on the vege of losing an election. The polls themselves are extremely specific, and routinely result in several decimal places. The falsification would be to report other than what they and their necessary adjustments tell us. Your proposal is on the order of, "don't tell me what the guy's batting average is when he's 467 of 1983, just tell me whether he's likely to get a hit or not."
   1107. Random Transaction Generator Posted: November 03, 2012 at 03:38 PM (#4291881)
Correct. We can compare them, and assess a correlation. My only point is that with a working sample of 4 or 5 elections, maybe 20 if you bring in Gubernatorial and Senatorial races, the correlation just can't be that strong.


Why do you keep saying the working sample is only 4 or 5 elections?
Each result from each state for the past elections counts as a data point to examine.
Multiply by the multiple polls taken of those states at various times in the run up to election day, and you're getting into the hundreds of data points for each election.
   1108. Steve Treder Posted: November 03, 2012 at 03:38 PM (#4291882)
Spoken like someone on the vege of losing an election. The polls themselves are extremely specific, and routinely result in several decimal places. The falsification would be to report other than what they and their necessary adjustments tell us. Your proposal is on the order of, "don't tell me what the guy's batting average is when he's 467 of 1983, just tell me whether he's likely to get a hit or not."

Yep.
   1109. snapper (history's 42nd greatest monster) Posted: November 03, 2012 at 03:39 PM (#4291884)
Spoken like someone on the vege of losing an election. The polls themselves are extremely specific, and routinely result in several decimal places. The falsification would be to report other than what they and their necessary adjustments tell us. Your proposal is on the order of, "don't tell me what the guy's batting average is when he's 467 of 1983, just tell me whether he's likely to get a hit or not."

No, my proposal is don't tell me the guy is 4 for his last 9, and base a prediction for today's game on it.
   1110. Morty Causa Posted: November 03, 2012 at 03:41 PM (#4291888)
Have you no soul, that you would so flippantly derail a Monty Python hijack?


As Bertie Wooster might say (a different definition of say here, snapper): rem acu tetigisti.

   1111. Joe Kehoskie Posted: November 03, 2012 at 03:44 PM (#4291893)
Spoken like someone on the vege of losing an election. The polls themselves are extremely specific, and routinely result in several decimal places.

But they're rarely reported that way. One of this week's polls that was reported as 49-48 Obama was actually 48.56 Obama to 48.49 Romney — a difference of one or two respondents.
   1112. Random Transaction Generator Posted: November 03, 2012 at 03:48 PM (#4291896)
But they're rarely reported that way. One of this week's polls that was reported as 49-48 Obama was actually 48.56 Obama to 48.49 Romney — a difference of one or two respondents.


If the headline/article writers want to distort it, that's their call. If Nate/RCP are using the real numbers, that's all that matters.

Are you advocating for more detailed results (48.56-48.49) or less detailed results (Nate rounds up)?
   1113. Jolly Old St. Nick Is A Jolly Old St. Crip Posted: November 03, 2012 at 03:51 PM (#4291900)
I realize it's not the same thing, but BITD half the 8 year olds on my block in DC owned "Daisy / Red Ryder" BB guns that were advertised on the back cover of comic books. They're not deadly or anything, but they can sure put some kid's eye out. They still make them, and I have no idea whether or not gun laws apply to them, but they sure didn't back then.


You city boys need to learn how those in the provinces once lived. In my country town where I grew up and went to school, farms kids not only got shotguns when they learned to walk practically, those who came to school in their pickup trucks had a gun rack over their rear window, which they parked on school grounds. (I don't think they locked the doors either.) And not once in those years did it occur to me, or any other kid, that if you got into a tiff with someone, he was going to go to his truck and get his gun.


You buy me a farm and a time machine and you're on.

And BTW they had to pry my Daisy off of my warm, sleeping body. Or maybe I just outgrew it around the same time I outgrew collecting baseball cards.
   1114. Joe Kehoskie Posted: November 03, 2012 at 03:53 PM (#4291901)
Are you advocating for more detailed results (48.56-48.49) or less detailed results (Nate rounds up)?

I'm simply saying that some of these comparisons are of different things. RCP's poll numbers are rounded off to the nearest whole number while Nate is going to four decimal places. A one-point election is tight enough, but 48.56 to 48.49 is beyond coin-flip.

Nate got burned three times on close Senate elections in 2010. It's interesting the amount of faith people have in Nate's ability to divine the outcome of the presidential election based on a similar batch of close polling numbers in Ohio and 1-2 other states.
   1115. Matt Clement of Alexandria Posted: November 03, 2012 at 03:57 PM (#4291902)
No, my proposal is don't tell me the guy is 4 for his last 9, and base a prediction for today's game on it.
I think we should get the claim on the table more clearly. The claim of poll accuracy has to do with the relative accuracy of polls for the last several elections. From 538 a couple days ago, this is how many points the state polling averages and the national polling averages missed to one side or the other. I've taken 1980 as a starting point to cherry-pick the worst polling year in modern history.

8.8, 7.2 - 1980
1.0, 0.6 - 1984
0.0, 1.5 - 1988
2.9, 1.0 - 1992
0.1, 5.1 - 1996
1.2, 3.2 - 2000
0.8, 1.0 - 2004
0.3, 0.0 - 2008

So far, there has been one election in the last eight in which both the state and national polls missed by more than two points. The last two elections, which have been by far the most extensively polled, have seen errors no greater than one percentage point.

This does not mean that errors of 5 points or more can't happen. They happened already in 1980. (Though that has a lot to do with the paucity of polling in 1980 and one or two really terrible polls from the week before, but I'm taking 1980 at face value for the sake of argument.) But given the data we have, it seems that betting on polling error of 2-3 points or more in Romney's direction - which is effectively what calling the election "a toss up" is - that is not a bet I would make.
   1116. Random Transaction Generator Posted: November 03, 2012 at 04:01 PM (#4291905)
I don't think the detail adds any value beyond an illusion of precision.


If Nate had rounded up his numbers, don't you think he'd take heat from people who say he's fudging the numbers?
When Nate simply lays out the numbers for people to see, and his percentage/averages have digits to show, why is it wrong to show them?
   1117. Random Transaction Generator Posted: November 03, 2012 at 04:03 PM (#4291906)
Nate got burned three times on close Senate elections in 2010. It's interesting the amount of faith people have in Nate's ability to divine the outcome of the presidential election based on a similar batch of close polling numbers in Ohio and 1-2 other states.


You seem to put a lot of faith in those three mistakes, without including the fact that he was correct on many other results.
   1118. Joe Kehoskie Posted: November 03, 2012 at 04:03 PM (#4291908)
But given the data we have, it seems that betting on polling error of 2-3 points or more in Romney's direction - which is effectively what calling the election "a toss up" is - that is not a bet I would make.

Two or three points nationwide or 2-3 points in 1-2 states?
   1119. Joe Kehoskie Posted: November 03, 2012 at 04:05 PM (#4291910)
You seem to put a lot of faith in those three mistakes, without including the fact that he was correct on many other results.

We didn't need Nate to tell us what would happen in California, Alabama, Arizona, or about 28 other Senate races. Nate's track record in the closest races is what's truly important here, and that track record isn't as good as some people seem to believe.
   1120. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 04:08 PM (#4291912)
Nate's track record in the closest races is what's truly important here, and that track record isn't as good as some people seem to believe.


What was his track record in states with close margins in 2008 and 2010?
   1121. McCoy Posted: November 03, 2012 at 04:10 PM (#4291914)
You seem to put a lot of faith in those three mistakes, without including the fact that he was correct on many other results.

I'd like to know what were the odds Nate was giving in those races. I'd also like to know if there truly only was 5 "contested" races.
   1122. spike Posted: November 03, 2012 at 04:11 PM (#4291917)
You seem to put a lot of faith in those three mistakes, without including the fact that he was correct on many other results.

At this point what else is there for ol' Joe? Even RCP is deserting him.
   1123. Joe Kehoskie Posted: November 03, 2012 at 04:11 PM (#4291918)
What was his track record in states with close margins in 2008 and 2010?

In the 2010 Senate races, Nate was 2-for-5 in the five closest races. He missed on Buck, Angle, and Miller.

In the 2010 House races, Nate underestimated GOP gains by over 20 percent.
   1124. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 04:14 PM (#4291919)
In the 2010 Senate races, Nate was 2-for-5 in the five closest races. He missed on Buck, Angle, and Miller.


That's not what I asked, and it makes me suspicious that you might be cherry-picking the data points to make Nate look bad.

Don't worry about it. I'll look it up myself and report back.
   1125. Joe Kehoskie Posted: November 03, 2012 at 04:16 PM (#4291921)
That's not what I asked, and it makes me suspicious that you might be cherry-picking the data points to make Nate look bad.

2010 wasn't a presidential election year, so there were no "states" for Nate to call.
   1126. spike Posted: November 03, 2012 at 04:17 PM (#4291923)
these arguments are potentially more intellectually coherent than the ones that propose that the race is "too close to call." It isn't. If the state polls are right, then Mr. Obama will win the Electoral College. If you can't acknowledge that after a day when Mr. Obama leads 19 out of 20 swing-state polls, then you should abandon the pretense that your goal is to inform rather than entertain the public.

From the man himself.
   1127. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 04:21 PM (#4291926)
2010 wasn't a presidential election year, so there were no "states" for Nate to call.


I know. That's why I said "states with close margins in 2008 and 2010." 2008: Senate, House, Presidential. 2010: Senate and House. And not "the five closest" but "all close margins." If Nate's really consistently wrong about close statewide polling, that should show up.

But like I say, I'll go ahead and look it up myself.
   1128. Joe Kehoskie Posted: November 03, 2012 at 04:22 PM (#4291927)
If you can't acknowledge that after a day when Mr. Obama leads 19 out of 20 swing-state polls, then you should abandon the pretense that your goal is to inform rather than entertain the public.

Nate's increasing defensiveness seems to betray some uncertainty. Otherwise, why not just sit back and bask in the glory of being right on Tuesday?

Beyond that, Nate knows damn well that a lot of those "19 out of 20 swing-state polls" were churned out by Dem-leaning pollsters simply for narrative purposes.
   1129. Tilden Katz Posted: November 03, 2012 at 04:22 PM (#4291928)
Fivethirtyeight's projections for Colorado, Nevada, and Alaska.
   1130. spike Posted: November 03, 2012 at 04:23 PM (#4291929)
Not to worry - Michael Barone calls it 315- 223 for Romney!

/thought about including a couple of quotes, but really, you should read the thing in situ.
   1131. McCoy Posted: November 03, 2012 at 04:25 PM (#4291931)
I took a look at the election results and it appears there were 7 close races and not 5.
Colorado
Alaska
Nevada
Illinois
Pennsylvania
Washington
Wisconsin

Nate got 4 of those 7 right.
   1132. Joe Kehoskie Posted: November 03, 2012 at 04:26 PM (#4291932)
I know. That's why I said "states with close margins in 2008 and 2010." 2008: Senate, House, Presidential. 2010: Senate and House. And not "the five closest" but "all close margins."

You'll struggle to find more than five or six close margins in the 37 2010 U.S. Senate races. Nate went 2-for-5 or 3-for-6 in the closest 2010 Senate races, and he underestimated the GOP's gains in the House by over 20 percent.

If others want to trust Nate's model 100 percent, that's up to them, but after Nate's record in 2010, I'm not willing to trust Nate's opinion that a 2-point Obama lead in Ohio makes him an ~85 percent favorite to win the entire presidential election.
   1133. Gold Star - just Gold Star Posted: November 03, 2012 at 04:26 PM (#4291933)
Hasn't it been well established that no pollster/aggregator really projected the degree of GOP's 2010 House blowout? And that Silver was by no means an outlier?
   1134. Random Transaction Generator Posted: November 03, 2012 at 04:27 PM (#4291934)
Nate's increasing defensiveness seems to betray some uncertainty.


Hehe. That's pretty funny.

People write articles that attack him personally, and when he defends himself and the numbers, he's "defensive" and "uncertain"?

Come on.
   1135. Tilden Katz Posted: November 03, 2012 at 04:28 PM (#4291936)
Hasn't it been well established that no pollster/aggregator really projected the degree of GOP's 2010 blowout? And that Silver was by no means an outlier?


Yes, and that because the vast majority of House districts are unpolled there is a great deal more uncertainty in forecasting the House as compared to Senate races and especially the Presidency.
   1136. Joe Kehoskie Posted: November 03, 2012 at 04:29 PM (#4291937)
I took a look at the election results and it appears there were 8 close races and not 5.
Colorado
Alaska
Nevada
Illinois
Illinois
Pennsylvania
Washington
Wisconsin

Nate got 5 of those 8 right.

You counted Illinois twice, while Washington and Wisconsin were 5-point margins.
   1137. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 04:29 PM (#4291938)
I have a hard time believing that you're actually so dense and so hyper-partisan that you can't/won't understand why 96% of poll respondents a few days before an election are labeled as likely voters. If it's not party ID it's LV screens or biased polling or whatever, anything to argue that Romney is actually leading the race. Never mind that the reason that Obama might be outperforming fundamentals is that Romney is a terrible candidate running on a terrible platform of more money for the rich, less help for the poor, more wars in the Middle East, interference in women's healthcare, and regression in social progress. If the fundamentals were neutral for Obama he would be crushing Romney because the right wouldn't be able to use scary economic doom-saying to hide how their platform is crap for the majority of Americans.
To this excellent post I'll add only that I'm not quite as surprised that density or hyperpartisanship is blinding someone to plain math. After all, the inability to obtain and marshal facts in an objective manner is part of what leads someone, these days, to vote Republican.

You know this though, you have to know. You're just ignoring it because you can use horribly faulty logic to twist it into another claim of poll bias and ignore the fact that your candidate is losing.
I don't think he does, though. I suspect the inability to marshal facts isn't something that can be turned on and off at will.

It does also seem to be the case that those who can't believe Romney is likely to lose are imagining some other scenario, where in fact it's Teddy Roosevelt (or someone) running on the GOP ticket, instead of the most plainly unqualified candidate in memory.
   1138. Gold Star - just Gold Star Posted: November 03, 2012 at 04:30 PM (#4291940)
Not to worry - Michael Barone calls it 315- 223 for Romney!
Yeesh. Of the consensus swing states (OH, FL, VA, NV, CO), Obama's only win is in Nevada? And he loses PA?
   1139. McCoy Posted: November 03, 2012 at 04:30 PM (#4291941)
Hehe. That's pretty funny.

People write articles that attack him personally, and when he defends himself and the numbers, he's "defensive" and "uncertain"?

Come on.


Reminds me of the whole Barry Bonds saga/steroid saga. He defends himself too vigorously, he isn't defending himself enough, if they're lying why isn't he suing, Clemens sued-that doesn't mean anything, so on and so on. People create will make anything fit the narrative they want to tell or believe.
   1140. Joe Kehoskie Posted: November 03, 2012 at 04:32 PM (#4291944)
Hasn't it been well established that no pollster/aggregator really projected the degree of GOP's 2010 House blowout? And that Silver was by no means an outlier?

So we're back to the "faulty polling data" defense?

Nate's a genius if he's right, and it's someone else's fault if he's wrong. Great work if you can get it.
   1141. Joe Kehoskie Posted: November 03, 2012 at 04:34 PM (#4291947)
To this excellent post I'll add only that I'm not quite as surprised that density or hyperpartisanship is blinding someone to plain math. After all, the inability to obtain and marshal facts in an objective manner is part of what leads someone, these days, to vote Republican.

Please explain the math or logic in which a 96 percent LV poll is representative of an electorate with ~72 percent actual turnout.
   1142. Tilden Katz Posted: November 03, 2012 at 04:36 PM (#4291950)
You counted Illinois twice, while Washington and Wisconsin were 5-point margins.


Both of those were closer than Harry Reid's 5.7 margin of victory over Sharron Angle. On a related note, what would have been the reaction if, say, Elizabeth Warren threatened to start killing politicians if she wasn't elected the way Angle did?
   1143. Joe Kehoskie Posted: November 03, 2012 at 04:37 PM (#4291951)
Both of those were closer than Harry Reid's 5.7 margin of victory over Sharron Angle.

Which Nate got wrong by ~8 points. (He had Angle +3.)

On a related note, what would have been the reaction if, say, Elizabeth Warren threatened to start killing politicians if she wasn't elected the way Angle did?

Probably much more muted than with Angle. Warren would only be using a bow and arrow.
   1144. McCoy Posted: November 03, 2012 at 04:40 PM (#4291953)
Nate's model for the 2010 senate probably had a 95% chance of happening as predicted. In the end he got 92% of his picks right. If Nevada had been polled better he would have gotten 95% of his picks right but that is simply a what if not a justification that he was still right. 92% is pretty darn good.

Now then the next step is to look at how far off he was in each prediction and compare that to how many polls he had to make those predictions and then compare all that work to what he is doing with the Presidential election. I would think the MoE of for midterm senatorial elections is greater than for Presidential elections. His senate predictions had a lot more Silver variables cooked into the numbers than his Presidential election numbers do the week before the election.

   1145. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 04:41 PM (#4291954)
I took a look at the election results and it appears there were 8 close races and not 5.
Colorado
Alaska
Nevada
Illinois
Illinois
Pennsylvania
Washington
Wisconsin

Nate got 5 of those 8 right.


Was Illinois so close it counts twice?
   1146. McCoy Posted: November 03, 2012 at 04:43 PM (#4291958)
Was Illinois so close it counts twice?

I saw the mistake and changed it already.
   1147. Lassus Posted: November 03, 2012 at 04:45 PM (#4291960)
Please explain the math or logic in which a 96 percent LV poll is representative of an electorate with ~72 percent actual turnout.

I know little about statistics or polling, but I'm going to say because if actual turnout is around 72%, the "likely voter" figure is 96% of that amount. I'll assume I've screwed it up, so someone just let me know how.
   1148. Gold Star - just Gold Star Posted: November 03, 2012 at 04:46 PM (#4291961)
Was Illinois so close it counts twice?
Two races: Live voters and dead.

"That's the Chicago way!"

/Sean Connery
   1149. DKDC Posted: November 03, 2012 at 04:47 PM (#4291962)
I would think the MoE of for midterm senatorial elections is greater than for Presidential elections.


If that's the case, shouldn't Nate's model account for that? He shouldn't have the same probability of a candidate winning with a +2 in a thinly polled Senate race that he would a presidential candidate with a persistant +2 across a large number of polls the week before election.
   1150. Joe Kehoskie Posted: November 03, 2012 at 04:47 PM (#4291963)
Nate's model for the 2010 senate probably had a 95% chance of happening as predicted. In the end he got 92% of his picks right. If Nevada had been polled better he would have gotten 95% of his picks right but that is simply a what if not a justification that he was still right. 92% is pretty darn good.

Giving Nate credit for being right on 30 Senate races that any political neophyte could have predicted is little more than stats-padding. All that really matters is Nate's track record in the closest elections.
   1151. Joe Kehoskie Posted: November 03, 2012 at 04:51 PM (#4291967)
I know little about statistics or polling, but I'm going to say because if actual turnout is around 72%, the "likely voter" figure is 96% of that amount. I'll assume I've screwed it up, so someone just let me know how.

You assumed correctly.

(Sorry, Lassus, couldn't resist.)

If actual turnout is 72 percent, then a poll with a good LV screen should identify only about 72 percent of RV respondents as LV. Otherwise, you'll be over-counting LV relative to the electorate, which means the results are probably skewed one way or the other (unless non-respondents split exactly according to party ID, which is unlikely).
   1152. Random Transaction Generator Posted: November 03, 2012 at 04:56 PM (#4291973)
Giving Nate credit for being right on 30 Senate races that any political neophyte could have predicted is little more than stats-padding. All that really matters is Nate's track record in the closest elections.


Did Dick Morris get them all right?
   1153. Joe Kehoskie Posted: November 03, 2012 at 04:57 PM (#4291975)
Did Dick Morris get them all right?

Dick Morris is a pundit/storyteller. He's not giving odds to four decimal places.
   1154. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 05:02 PM (#4291982)
If that's the case, shouldn't Nate's model account for that? He shouldn't have the same probability of a candidate winning with a +2 in a thinly polled Senate race that he would a presidential candidate with a persistant +2 across a large number of polls the week before election.
I'd assume that shows up in his estimates. If I poll ten voters and eight tell me Obama's their man, it might budge me off a 50/50 estimate, but not by more than a hundredth of a percent. If I poll ten thousand voters and eight thousand say they'll vote Obama, I'll predict an Obama win effectively 100% of the time.

The number polled should definitely affect the estimates. I can't imagine it's not 'baked in' to the number when Silver says there is a 83.17% likelihood of Obama winning. That figure is a combination of polling results and uncertainty due to sample size.

Hey, if the election goes to Congress and the House selects Romney for Prez, can it pick anyone for Veep? Like, say, Obama? Granted, his office would be a few miles down the road from the White House, but it's not a terrible 'just in case' strategy for a Dem Senate.

Okay, I'm getting goofy.
   1155. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 05:05 PM (#4291984)
Ugh. I regret assigning myself work!

Okay, here's what I have. I decided a "close race" was anything that ended up within 4%, which gave me these results:

2008 Presidential Race: five "close races"; 528 was 4-1. (1)
2008 Senate Race: four "close races"; 528 was 4-0 (2)
2010 Senate Race: four "close races"; 528 was 2-2 (3)

(1) Correct on Florida, Missouri, Montana, and North Carolina; wrong on Indiana (predicted R; it went D)
(2) Correct on Alaska, Georgia, Minnesota, and Oregon
(3) Correct on Illinois and Pennsylvania; wrong on Colorado and Alaska
If you accept that the closest races are the hardest to call, I think 10-3 is a pretty good record.

I would also like to apologize to Joe and withdraw my accusation of cherry-picking the data. His "five closest races" is actually nicer to Nate than my metric, which omits a race Nate got right. Also, looking this up was a pain, so any sensible person would have avoided doing it.

(Disclaimer: It's possible I got something wrong. If so, I promise it was an accident.)
   1156. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 05:09 PM (#4291985)
(Oh! And I just thought of a new explanation for the "Likely Voter" thing: clearly, there's a difference between "likely" and "guaranteed". If only 75% of voters make the jump from "likely to vote" to "actually voting", you get from 96% to 72%.)
   1157. McCoy Posted: November 03, 2012 at 05:09 PM (#4291986)
If that's the case, shouldn't Nate's model account for that? He shouldn't have the same probability of a candidate winning with a +2 in a thinly polled Senate race that he would a presidential candidate with a persistant +2 across a large number of polls the week before election.

I believed he tried to adjust for that and in 3 close races he got it wrong with one of the times happening because the polling was seriously flawed. After the election he studied his numbers and has tried to improve upon them. We'll see if it works or not.

I know little about statistics or polling, but I'm going to say because if actual turnout is around 72%, the "likely voter" figure is 96% of that amount. I'll assume I've screwed it up, so someone just let me know how.


This whole thing is nothing but troll stupidity. Joe is either pretending he doen't understand how polls work or is genuinely stupid when it comes to polls. Joe thinks that every single person that gets contacted is part of the poll. He doesn't understand that the only people that get counted in the poll are people who actually take the poll and that at this point in the game the only people taking part in polls are people very much likely to vote.

If a polling agency calls me and I don't pick up the phone my not picking up the phone isn't counted as part of the polling group. If I pick up the phone and they ask me to take part in a poll and I say no, again I am not counted as part of the poll. Joe does not understand that or is pretending to not understand that. You go back and look at all the polls that are done by phone and you'll see that almost all if not all of the polls have a higher LV% than actually what happens and that as we get closer to the election the LV% increases. Not taking the poll is part of the screening process. Is it perfect? Of course not but not for the reasons that Joe is trying to use.

Polling only people who are actually going to vote doesn't skew a thing. That is just plain old stupidity or trolling at its finest.
   1158. Matt Clement of Alexandria Posted: November 03, 2012 at 05:10 PM (#4291987)
(Not that I'm going to do the work, and thanks Monty for collecting the data, but it seems like any double-check on Nate should include all the states he got wrong, and the <4% criterion excludes the miss in Nevada, where the polls massively and systematically overestimated Angle's support. She lost by 6 when almost all the polls had her up by several points. It seems likely that Nevada pollsters failed to properly survey Hispanic voters.)
   1159. McCoy Posted: November 03, 2012 at 05:13 PM (#4291989)
Okay, here's what I have. I decided a "close race" was anything that ended up within 4%, which gave me these results:

The only issue I have with this is that the criteria for selection should be a race that was predicted to be within 4 points and not the other way around.
   1160. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 05:18 PM (#4291992)
Isn't another important point how Nate compares to other pollsters? It's good to know he's right x% of the time. It's also good to know he's in the yth percentile of pollsters. Without the latter, x doesn't mean quite as much.
   1161. Jolly Old St. Nick Is A Jolly Old St. Crip Posted: November 03, 2012 at 05:19 PM (#4291993)
Not to worry - Michael Barone calls it 315- 223 for Romney!

Michael Barone, October 29, 2008, six days before the election, accompanied by Chet Baker:

The tracking polls seem to show the presidential race tightening. Rasmussen numbers released this morning show Barack Obama ahead of John McCain by only 50 percent to 47 percent—the narrowest margin in Rasmussen polls for more than a month and the first time McCain has been over 46 percent since September 24 (nine days after the collapse of Lehman Brothers and two days before the first debate). Gallup's tracking released yesterday showed McCain behind by only 49 percent to 47 percent on its traditional-turnout model but behind by a much larger 51 percent to 44 percent on its expanded model.

John Zogby's numbers yesterday showed a 49 percent-to-44 percent margin for Obama, considerably smaller than the one he had a few days earlier.

Against these numbers one must weigh polls in battleground states showing Obama doing just about as well as he has been since the financial crisis hit in mid-September. And the respected Pew Research poll shows Obama out in front by a whopping 53 percent to 39 percent. I'm reluctant to dismiss Pew as an outlier, but if you do, the realclearpolitics.com average of recent polls looks like Obama 49.6 percent, McCain 44.8 percent, a margin of 4.8 percentage points—the smallest Obama margin in RCP averages since September 30.

This sounds plausible to me. Hypothesis: The McCain "Joe the Plumber" high-taxes issue is having some impact. So are doubts, kindled by a typically verbose Joe Biden comment, about how Obama would handle an international crisis. Is this the beginning of a McCain surge? Possibly. It's beginning to look like something more than statistical noise. But it's hard to be sure at this point.
   1162. McCoy Posted: November 03, 2012 at 05:20 PM (#4291994)
Hey, if the election goes to Congress and the House selects Romney for Prez, can it pick anyone for Veep? Like, say, Obama? Granted, his office would be a few miles down the road from the White House, but it's not a terrible 'just in case' strategy for a Dem Senate.

Okay, I'm getting goofy.


Biden could remain as VP in an electoral tie and could become President in a house deadlock.
   1163. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 05:23 PM (#4291995)
Is this the beginning of a McCain surge? Possibly. It's beginning to look like something more than statistical noise.
And called McMentum, no doubt.

McCoy, I know Biden could, but was curious as to whether the Senate had only the choice between Biden and Ryan. I can't find specific info on that.
   1164. Gold Star - just Gold Star Posted: November 03, 2012 at 05:23 PM (#4291996)
Michael Barone, October 29, 2008, six days before the election...
Why aren't pundits proven consistently wrong shamed out of the business? Hell, in Italy, they'd be imprisoned.
   1165. Joe Kehoskie Posted: November 03, 2012 at 05:24 PM (#4291998)
This whole thing is nothing but troll stupidity. Joe is either pretending he doen't understand how polls work or is genuinely stupid when it comes to polls. Joe thinks that every single person that gets contacted is part of the poll. He doesn't understand that the only people that get counted in the poll are people who actually take the poll and that at this point in the game the only people taking part in polls are people very much likely to vote.

It's funny how things work around here. If a poll shows a D+8 advantage in 2012, an even higher Dem advantage than 2008, we're told that the poll result is representative of the electorate, and anyone who questions it is a "poll truther." But now, we're told that a poll that shows 96 percent of RV to be LV is not representative but it's somehow still accurate. Or something.

If a polling agency calls me and I don't pick up the phone my not picking up the phone isn't counted as part of the polling group. If I pick up the phone and they ask me to take part in a poll and I say no, again I am not counted as part of the poll. Joe does not understand that or is pretending to not understand that. You go back and look at all the polls that are done by phone and you'll see that almost all if not all of the polls have a higher LV% than actually what happens and that as we get closer to the election the LV% increases. Not taking the poll is part of the screening process. Is it perfect? Of course not but not for the reasons that Joe is trying to use.

In McCoy's fantasyland, non-voting RV don't answer the phone for 180 days prior to an election. Comical.
   1166. Jolly Old St. Nick Is A Jolly Old St. Crip Posted: November 03, 2012 at 05:24 PM (#4291999)
2008 Presidential Race: five "close races"; 528 was 4-1. (1)
2008 Senate Race: four "close races"; 528 was 4-0 (2)
2010 Senate Race: four "close races"; 528 was 2-2 (3)

(Disclaimer: It's possible I got something wrong. If so, I promise it was an accident.)


(smile)
   1167. McCoy Posted: November 03, 2012 at 05:28 PM (#4292001)
McCoy, I know Biden could, but was curious as to whether the Senate had only the choice between Biden and Ryan. I can't find specific info on that.

They can only choose from the two candidates with the highest electoral votes. It is in the 12th amendment.

I added it later but if the House deadlocks Biden would become the President.
   1168. Best Regards, President of Comfort, Esq. Posted: November 03, 2012 at 05:28 PM (#4292003)
McCoy, I know Biden could, but was curious as to whether the Senate had only the choice between Biden and Ryan. I can't find specific info on that.
12th Amendment.

If there's a tie, the incoming House chooses between the top three electoral vote recipients for President, each state gets one vote. The incoming Senate chooses between the top two electoral vote recipients for Vice President. The sitting Vice President breaks a tie in the Senate. If the House cannot choose a President, the choice of the Senate becomes President.

If a faithless elector casts a ballot for someone other than Obama or Romney, the House can choose that person. If there are 135 faithless electors who cast a ballot for someone other than Biden or Ryan for Vice President, the Senate can choose that person.
   1169. Joe Kehoskie Posted: November 03, 2012 at 05:30 PM (#4292005)
Why aren't pundits proven consistently wrong shamed out of the business? Hell, in Italy, they'd be imprisoned.

I don't see anything in #1161 that was laughably wrong. That last paragraph is hardly a prediction of a McCain win.

I'm not the biggest fan of political pundits, and I'll be in favor of a wholesale purge of the current crop if Romney wins, but it's hard to name many people who might know more about U.S. politics — or have been right more often — than Michael Barone.
   1170. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 05:31 PM (#4292006)
The only issue I have with this is that the criteria for selection should be a race that was predicted to be within 4 points and not the other way around.


I agree! But I couldn't find that, and I could find the actual results.
   1171. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 05:32 PM (#4292007)
(smile)


Curses!
   1172. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 05:33 PM (#4292008)
Jeez. If you guys are going to refer to the Constitution, there'll be no talking to you.

[red face]

Thanks, gents.
   1173. McCoy Posted: November 03, 2012 at 05:36 PM (#4292009)
The sitting VP does not get to break a tie in the case of picking the VP. You need a majority of Senators to vote to pick a VP.
   1174. Jolly Old St. Nick Is A Jolly Old St. Crip Posted: November 03, 2012 at 05:39 PM (#4292012)
I'm not the biggest fan of political pundits, and I'll be in favor of a wholesale purge of them if Romney wins, but it's hard to name many people who might know more about U.S. politics — or have been right more often — than Michael Barone.

That first part is indisputable, but the second part is an unsubstantiated assertion, unless you can show evidence to back it up.



   1175. Mefisto Posted: November 03, 2012 at 05:39 PM (#4292013)
I added it later but if the House deadlocks Biden would become the President.


No way the House deadlocks. The Rs control a comfortable majority of the states and are likely to keep that.
   1176. McCoy Posted: November 03, 2012 at 05:40 PM (#4292014)
No way the House deadlocks. The Rs control a comfortable majority of the states and are likely to keep that.

I didn't say it was going to happen just explaining what would happen if the House deadlocks and time runs out.
   1177. Tilden Katz Posted: November 03, 2012 at 05:41 PM (#4292015)
A majority of all Senators, or a majority of voting Senators? I don't believe Mark Kirk has voted since he had his stroke, so could Biden be elected on a 50-49 vote? (purely academic, since the odds of there being a 269-269 tie AND the Democrats holding fewer than 51 seats is extremely low)
   1178. Mefisto Posted: November 03, 2012 at 05:41 PM (#4292016)
The sitting VP does not get to break a tie in the case of picking the VP. You need a majority of Senators to vote to pick a VP.


This is unclear and a very interesting issue. Better view is probably that sitting VP can break a tie by voting for himself. One of those issues where the Constitution's language can lead to a situation where it conflicts with basic ideas of fairness.
   1179. Random Transaction Generator Posted: November 03, 2012 at 05:46 PM (#4292018)
Dick Morris is a pundit/storyteller. He's not giving odds to four decimal places.


Of course not. He's not using any numbers at all for his process (except for his secret polls), so I don't expect him to show them in his predictions.

However, if you had to choose one prediction, Dick Morris' or Nate Silver's, which would you feel more confident backing?
   1180. thok Posted: November 03, 2012 at 05:55 PM (#4292021)
If a faithless elector casts a ballot for someone other than Obama or Romney, the House can choose that person


Ron Paul 2012! (I'm not a Ron Paul supporter, but this would be either bloody hilarious or tragic or both.)
   1181. McCoy Posted: November 03, 2012 at 05:59 PM (#4292024)
A majority of all Senators, or a majority of voting Senators? I don't believe Mark Kirk has voted since he had his stroke, so could Biden be elected on a 50-49 vote? (purely academic, since the odds of there being a 269-269 tie AND the Democrats holding fewer than 51 seats is extremely low)

A majority of all Senators. It is believed based on the wording that a VP could not break the tie. It is also possible for the Republicans in the Senate to filibuster the vote for VP.
   1182. tshipman Posted: November 03, 2012 at 06:10 PM (#4292031)
It's funny how things work around here. If a poll shows a D+8 advantage in 2012, an even higher Dem advantage than 2008, we're told that the poll result is representative of the electorate, and anyone who questions it is a "poll truther." But now, we're told that a poll that shows 96 percent of RV to be LV is not representative but it's somehow still accurate. Or something.


At this point, you should base your arguments on something other than polls. You're like someone saying that we shouldn't use stats to determine who the best players in the league are, and then you go around citing batting average and RBI.

Either the polls are systemically and widely incorrect, or Romney is losing. Snapper is showing a decent way to argue as if you just believe the polls are all wrong.
   1183. zenbitz Posted: November 03, 2012 at 06:11 PM (#4292032)
Man there is either a lot of trolling or bad math here.

A close senate race is by definition a 50-50 proposition. So Nates expectation should be to miss 2-3/5 or 3-4/7.
If he got 7/7 he would have just have been lucky.

Of course the OPPOSITE is true for the Ec. It's not a Coin flip because Romney needs several states, not just Virginia
   1184. zenbitz Posted: November 03, 2012 at 06:20 PM (#4292035)
Oh and McCoy explains the "lv" gap quite well.
   1185. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 06:29 PM (#4292036)
I think I sort of half agree with this criticism. There's not really all that much to the model beyond the basic concept of aggregating all the available polling data. If the data is crap, the model can't fix it. So if Nate is right, it mostly means that the polls were right, and not all that much more than that.
Given that Nate works the data at least somewhat differently from other pollsters, if he's 'right' we'll have a sense of how right he was by comparing his predictions against that of other pollsters.

It's also possible that the raw data is good, but that it's being misconstrued by various pollsters (perhaps they're not accounting sufficiently for the tendencies of cell phone users, for example). A good agregator can draw better conclusions from unclear, raw data than a poor agregator.

but it's hard to name many people who might know more about U.S. politics — or have been right more often — than Michael Barone.
Heehee. Not Dick Morris?

Unless by 'right more often' he meant something else entirely...
   1186. Danny Posted: November 03, 2012 at 06:40 PM (#4292041)
I know little about statistics or polling, but I'm going to say because if actual turnout is around 72%, the "likely voter" figure is 96% of that amount. I'll assume I've screwed it up, so someone just let me know how.


I explained this to Joe (and McCoy) several pages ago, but he's still repeating this nonsense. A polling firm found (in one poll) that 96% of people who say they are registered to vote are likely to vote. While it's true that only ~72% of people who are actually registered to vote actually vote, the correct comparison is to the percent of people who say they are registered to vote who actually vote.

Since ~90% of people who say they are registered to vote actually voted in 2008, the pollster's likely voter screen appears to be reasonable. The likely explanation is that some people don't realize they're registered to vote, and the people who do realize they're registered are much more likely to actually vote than those who are registered but don't realize it.
   1187. Joe Kehoskie Posted: November 03, 2012 at 06:58 PM (#4292048)
Either the polls are systemically and widely incorrect, or Romney is losing. Snapper is showing a decent way to argue as if you just believe the polls are all wrong.

Yes, if by "systematically and widely," you mean "in Ohio and maybe 1-2 other states."

***
A close senate race is by definition a 50-50 proposition. So Nates expectation should be to miss 2-3/5 or 3-4/7.
If he got 7/7 he would have just have been lucky.

Of course the OPPOSITE is true for the Ec. It's not a Coin flip because Romney needs several states, not just Virginia

So you'd expect Nate to be wrong in about ~50 percent of toss-up Senate races, but you're expecting him to bat a thousand in close state races in the Electoral College?

Oh and McCoy explains the "lv" gap quite well.

Yes, only likely voters answer the phone for 90 to 180 days before elections. We can call this the Watson Rule.
   1188. Joe Kehoskie Posted: November 03, 2012 at 07:06 PM (#4292055)
I explained this to Joe (and McCoy) several pages ago, but he's still repeating this nonsense. A polling firm found (in one poll) that 96% of people who say they are registered to vote are likely to vote. While it's true that only ~72% of people who are actually registered to vote actually vote, the correct comparison is to the percent of people who say they are registered to vote who actually vote.

Since ~90% of people who say they are registered to vote actually voted in 2008, the pollster's likely voter screen appears to be reasonable. The likely explanation is that some people don't realize they're registered to vote, and the people who do realize they're registered are much more likely to actually vote than those who are registered but don't realize it.

This logic was incorrect yesterday and it remains incorrect today.

In the Gallup poll on which you're relying, over 40,000,000 registered voters — 40,000,000 voters — went missing. Unless you believe those 40,000,000 non-respondents broke down exactly according to party lines, an LV screen that pretends these 40,000,000 voters don't exist will be heavily skewed toward whichever party's voters are most likely to respond to the poll.

Beyond that, explaining away these 40,000,000 registered voters by surmising they're "registered but don't realize it" is a huge leap that's unsupported by any evidence. Are you seriously claiming that almost a quarter of the American electorate is unaware they're registered to vote?
   1189. Monty Predicts a Padres-Mariners WS in 2016 Posted: November 03, 2012 at 07:06 PM (#4292056)
By the way, I just noticed that one of the tags for this thread is "mr president".
   1190. AROM Posted: November 03, 2012 at 07:10 PM (#4292059)
A note on RCP. They have a mostly arbitrary, possibly somewhat partisan poll screening method that gives them a rightward lean in their averages compared to Pollster, TPM, and 538. They don't include about 25% of publicly released polls, and their selection methods appear entirely subjective. I think that by making use of every existing poll not released by a campaign, the other poll averages are better options. If there were an RCP that handled all polls equally, I'd be interested to see how it compared to the more complex aggregation models at 538 and Pollster.


I did know RCP was right-leaning. Which to me is a feature, not a bug, since Nate is obviously left-leaning. The bias does not materially impact the end results of either, because both sites end up with the same results in every state except Virginia (and there it's only a tenth of a percentage point).
   1191. Johnny Temporary Posted: November 03, 2012 at 07:12 PM (#4292060)
Either the polls are systemically and widely incorrect, or Romney is losing. Snapper is showing a decent way to argue as if you just believe the polls are all wrong.


Snapper is making rational and coherent arguments, I think he's wrong, but he is being coherent. Someone else here is not- and has shown no ability and/or interest in being rational or coherent.

Anyway, looking at Colorado and Nevada 2010 is interesting- so Nate got them wrong- why?

First thing I notice looking at the polls listed on Wiki - neither eventual winner won a poll within 3-4 weeks of the election- second thing I notice going to Silver's site- both eventual winners did in fact win some polls near the end - even Reid- he was winning the RV polls- in both states there seems to have been a wider spread than usual between RV and LV results- my guess is that the LV screens were a tad too aggressive...

Of course those criticizing Silver are not actually interested in WHY Silver got something wrong- they solely want to point out that Silver missed some states in the past as a jumping off point for their argument that he's wrong NOW. Of course if they look under the hood and see that, aha big split between LV and RC means maybe you should regress a bit towards LV- well that is most definitely not something the Amti-Nates want to even contemplate.


   1192. Shredder Posted: November 03, 2012 at 07:14 PM (#4292062)
Yes, only likely voters answer the phone for 90 to 180 days before elections. We can call this the Watson Rule.
Joek apparently believes that caller ID doesn't exist. Joek apparently also believes that every person who answers their phone when a pollster calls is somehow obligated to actually take part in the whole process once the call begins. He thinks the following NEVER EVER happens:

**ring**ring**

Citizen: Hello?
Pollster: Hi, we're conducting a poll for....
Citizen: *click*

Personally, I think that probably happens quite a bit, and furthermore, the person more likely actually take the poll is the person who is probably actually interested in voting, what someone may call a "likely voter".

   1193. Johnny Temporary Posted: November 03, 2012 at 07:15 PM (#4292063)
I did know RCP was right-leaning. Which to me is a feature, not a bug, since Nate is obviously left-leaning.


Oh when they started in 2000 they were very openly partisan- they've put a damper on their own rhetoric- but there is a definite rightward lean to the articles and columns they link to on their blog page- not as bad as Drudge (or Fox)-

but no they do not include as many polls as 538- and 538 does not include as many as Pollster
   1194. McCoy Posted: November 03, 2012 at 07:16 PM (#4292064)
A close senate race is by definition a 50-50 proposition. So Nates expectation should be to miss 2-3/5 or 3-4/7.
If he got 7/7 he would have just have been lucky.

Of course the OPPOSITE is true for the Ec. It's not a Coin flip because Romney needs several states, not just Virginia


The only issue with that is that in the three races he got wrong he put the odds of winning each of those elections at higher than 60% so Nate wasn't saying it was a coin toss in those states.
   1195. calhounite Posted: November 03, 2012 at 07:16 PM (#4292065)
People are automatons. Better way of saying it is that people are jellybeans. Take a sample of 1000 red and blue jellybeans out of a jar holding a mixture of a billion jellybeans, can get an accurate measurement of number of red and blue jellybeans in the jar.

But people don't really rise to the status of jellybeans. It's even worse than that. Don't even need 1000 jellybean people. One is information overload. Just Billy Bob. Don't even need to ask about the election. One properly analyzed Billy Bob fart could decide any election held anywhere ever.

This election is over. Finished. Done. Kaput. My dog has a better chance than Romney. That is equal to the odds of turning around a 100 mile long aircraft carrier mired in a 2 inch deep, 2 inch wide dry drainage ditch.

   1196. Danny Posted: November 03, 2012 at 07:18 PM (#4292067)
In the Gallup poll on which you're relying, over 40,000,000 registered voters — 40,000,000 voters — went missing.

It's not a Gallup poll. It's census data from the Current Population Survey.
Beyond that, explaining away these 40,000,000 registered voters by surmising they're "registered but don't realize it" is a huge leap that's unsupported by any evidence. Are you seriously claiming that almost a quarter of the American electorate is unaware they're registered to vote?

I'm saying that the census found that a lot of people didn't realize they were registered to vote, and that's roughly what the census has found each of the past four elections (see Table 1). It's not an outlier result.
   1197. McCoy Posted: November 03, 2012 at 07:20 PM (#4292069)
Joek apparently believes that caller ID doesn't exist. Joek apparently also believes that every person who answers their phone when a pollster calls is somehow obligated to actually take part in the whole process once the call begins. He thinks the following NEVER EVER happens:

Wait, this is his reason for thinking LV screens are wrong? Holy christ, that is either sheer stupidity or just big time trolling.

Again, polling centers call a bunch of people but only about 8% of them actually take the poll. People who take the poll are more inclined to vote than people who do not take the poll thus as we get closer to the election the % of LV gets higher and higher.
   1198. Joe Kehoskie Posted: November 03, 2012 at 07:25 PM (#4292072)
He thinks the following NEVER EVER happens:

**ring**ring**

Citizen: Hello?
Pollster: Hi, we're conducting a poll for....
Citizen: *click*

Personally, I think that probably happens quite a bit, and furthermore, the person more likely actually take the poll is the person who is probably actually interested in voting, what someone may call a "likely voter".

LOL. The idea that only likely voters answer the phone for the 90 or 180 days preceding an election is comical. Any registered voter who answers the phone and declines to participate would count as a data point, but some of these polls are claiming more than 96 RVs in 100 are agreeing to participate and, thus, are LVs. It's nonsense.
   1199. Johnny Temporary Posted: November 03, 2012 at 07:26 PM (#4292073)
Wait, this is his reason for thinking LV screens are wrong? Holy christ, that is either sheer stupidity or just big time trolling.


No his reason for thinking LV screens are wrong starts and ends with the fact that his candidate appears to be losing.
   1200. Jack Carter, calling Beleaguered Castle Posted: November 03, 2012 at 07:29 PM (#4292074)
Personally, I think that probably happens quite a bit, and furthermore, the person more likely actually take the poll is the person who is probably actually interested in voting, what someone may call a "likely voter".
Isn't the landline response rate around 3%?

By the way, I just noticed that one of the tags for this thread is "mr president".
We might as well just shorten that to "Mr. Obama".


In other news, a man sued his wife for delivering an ugly baby.

He won.


.
Page 12 of 114 pages ‹ First  < 7 8 9 10 11 12 13 14 15 16 17 >  Last ›

You must be Registered and Logged In to post comments.

 

 

<< Back to main

BBTF Partner

Support BBTF

donate

Thanks to
Harveys Wallbangers
for his generous support.

Bookmarks

You must be logged in to view your Bookmarks.

Hot Topics

NewsblogOT: Monthly NBA Thread - September 2014
(6 - 2:36am, Sep 02)
Last: RollingWave

NewsblogTrevor Hoffman's Hall of Fame induction seems inevitable
(7 - 2:30am, Sep 02)
Last: Infinite Joost (Voxter)

NewsblogPhoto of the day: Bill Murray, indy league ticket-taker
(103 - 2:27am, Sep 02)
Last: Robert in Manhattan Beach

NewsblogNitkowski: Wanted: Major League manager...sort of.
(8 - 2:07am, Sep 02)
Last: Robert in Manhattan Beach

NewsblogOMNICHATTER 9-1-2014
(40 - 2:01am, Sep 02)
Last: MNB

NewsblogAstros Fire Bo Porter
(57 - 1:54am, Sep 02)
Last: base ball chick

NewsblogRobothal: Changed [Manny] Ramirez enjoyed helping Cubs prospects grow
(13 - 1:27am, Sep 02)
Last: The Clarence Thomas of BBTF (scott)

Hall of MeritMost Meritorious Player: 1957 Ballot
(10 - 1:12am, Sep 02)
Last: Moeball

NewsblogHBT: Jorge Soler with an extra-base hit in each of his first five games
(2 - 1:02am, Sep 02)
Last: madvillain

NewsblogOT: Politics, September, 2014: ESPN honors Daily Worker sports editor Lester Rodney
(28 - 1:00am, Sep 02)
Last: Ray (RDP)

NewsblogRon Roenicke rips into home-plate umpire
(17 - 12:18am, Sep 02)
Last: Bunny Vincennes

NewsblogBlue Jays Acquire Mayberry Jr.
(7 - 12:10am, Sep 02)
Last: Infinite Joost (Voxter)

NewsblogAthletics Acquire Adam Dunn
(43 - 11:46pm, Sep 01)
Last: Pasta-diving Jeter (jmac66)

NewsblogOT: The Soccer Thread August, 2014
(986 - 11:25pm, Sep 01)
Last: The Clarence Thomas of BBTF (scott)

NewsblogOT:  2014 College Football pre-season thread
(101 - 11:17pm, Sep 01)
Last: Lance Reddick! Lance him!

Page rendered in 0.9417 seconds
52 querie(s) executed