User Comments, Suggestions, or Complaints | Privacy Policy | Terms of Service | Advertising
|
Demarini, Easton and TPX Baseball Bats
|
AllianceTickets.com has cheap MLB Tickets. Get all your Colorado Rockies Tickets, Seattle Mariners Tickets, San Francisco Giants Tickets and all your favorite baseball tickets here. We also carry cheap Denver Broncos Tickets, Seattle Seahawks Tickets and Denver Nuggets Tickets. |
For wholesale prices on baseball gifts and equipment, check these stores out! |
Page rendered in 0.6729 seconds
54 querie(s) executed
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.
Well, that's not exactly news, now is it?
538 has Obama at a 1.7% lead and winning the electoral college
RCP has Romney at a .9% lead and Obama wining the electoral college.
As far as I can tell virtually all aggregator sites say the election is going to be close but Obama is going to win the electoral college. So Nate is not exactly alone out on that "limb"
Yeah, that's useful.
2) If Silver deviates significantly from the national polling averages, then that will be a story. If the state and national polling averages underlying his model diverge significantly from RCP and Pollster, and RCP/Pollster are right and he's wrong, that will be a major blow to the credibility of his model.
3) It could be that Silver is underestimating uncertainty. There is no good way to model that which is unknown. It could be that, given traditional polling methodology, uncertainty is much larger than his model suggests. Maybe a 2 point Obama polling lead should only project to a 60-40 chance of an Obama win rather than 70-30 or 80-20. I don't think that failing to model uncertainty means the end of his credibility, but he has taken the step of modeling uncertainty and can be criticized if he has modeled it poorly.
(This goes back to #1 - it's not a criticism of his results, but of his method. That's where the most valuable critiques will come from.)
4) Say Nate's model projects a 95%+ chance of a Romney win, and then Obama wins, or vice versa. If this happens, and it isn't because Nate's model deviated from Pollster or RCP in its state and national averages, then there will have been a massive breakdown in public opinion polling. This will be a problem for polling aggregators and political scientists who have argued for the relative reliability of public opinion polling, but it will be a much bigger problem for the polling industry.
One important note here is that I don't believe Nate Silver's model adds that much value beyond what Pollster does. Nate does another step of aggregation, which is reasonably useful for readers, but doesn't actually produce anything that wasn't in the Pollster numbers to begin with. It's not "going out on a limb" to add up the state and national numbers into one aggregate total.
What value 538 provides, for the most part, comes from his writing and analysis. He's really good at explaining some complex methodological and statistical questions. I assume he'll retain those capacities even in the event of a polling disaster.
Yes, as I said above, I agree with this.
How about 91% (or 98%)? I'm pretty sure if Romney wins the EC, this guy is gonna get creamed.
If you're grading based on one projection, it *is* downright difficult to be wrong in any kind of relevant manner.
Google Goggle
We Accept You
We Accept You
How about 91% (or 98%)? I'm pretty sure if Romney wins the EC, this guy is gonna get creamed.
Silver, I'll defend to the wall. Wang, I won't. Nate's never hid the fact that he's a Democrat, but he's never crossed the line into the blatant advocacy that Wang, who mixes analysis with direct fundraising pleas, does. I believe at some level, you have to choose your hat, whether you want to play the advocate or the analyst.
So, to recap, PPP polls are worthless and biased because they provide full demographic crosstabs in their poll PDFs instead of in their press releases, which makes it too hard for you to find. And Rasmussen polls are totally fine and trustworthy because you think they might provide some of this information to subscribers.
I'm pretty sure if Romney wins the EC, this guy is gonna get creamed.
Middle class, is he?
I think the storm will be blamed by anyone who is badly wrong. It'll be believable. From my reading, it looks like the race is too close to call - sure, Obama has a decided advantage in the EC but that is built on lots of narrow leads in states. It isn't as if he is leading by 10% in a bunch of important states. The storm provides room for legitimate havoc and chaos as well as room for the spin-monsters to do their thing withouth much time for rebuttal (from both sides).
Not to mention those wildly inaccurate ESPN baseball projections. ;)
I think my bosses cringe anytime I'm doing a radio spot or making a blog comment to the effect that the goal of a projection system is to be slightly less horribly inaccurate than everyone else.
1) excluding Rand entirely and including it with some downgrade?
2) then averaging all equally vs rebalancing them based on past effects?
So RCP takes one extreme act of removal but then doesn't judge anything. Nate assumes all data is useful but needs to be assessed so assesses based upon a method he's using.
If you add Rand into the average at RCP and don't rebalance, you get an exact tie. In which case Nate looks less out on a limb than the comments here indicate.
Since RCP is emphatically not just an averager but is instead a subjective decision about what to include and what not to include, a subjective decision in keeping with the founders' explicit goals of increasing conservative coverage, then will its supporters here renounce it and refuse to visit it if Romney in fact does not win the popular vote?
If someone says that, and then asks if I'll stop visiting Nate, then I can deal with that question. But someone who won't deal with RCP's own subjectivity and then make demands upon other people is just concern trolling.
To me, 70-75% for an incumbent seems almost as close to a coin-flip as most incumbents will get, assuming fairly neutral/plain conditions and candidates (certainly neither candidate this year is doing anything special, and I don't sense economic/foreign policy conditions are really that unique this year either, partisan opinions aside).
It would be interesting to see what Nate's odds would have been for Reagan in '84, or Clinton in '96. Then you might get near 100% territory. Which suggests that Nate's model recognizes that 2012 is different and has downgraded the incumbent accordingly. Has he been downgraded enough? I guess we'll see, but the answer will be a lot more nuanced that your 100%-right-or-wrong assertions make it out to be.
The big difference between Nate and RCP on the projected national vote, however, has little to do with what polls are not included in the RCP average. The 538 model uses the state-by-state polling as evidence of the national race, and the state-by-state polling is consistent with a national race where Obama leads by about three points. So the 538 model aggregates the state and the national polling, creating an average of Obama +2 or so.
RCP uses only national polls in producing its national average, which creates a huge divergence between its popular and electoral vote projections.
I think one of the keys to Nate's rise to stardom in 2008 was the part of his brain that self-edited comments like that.
But who knows, the lack of such a disclaimer might be his undoing yet!
I didn't mean in actual voting - if it is perceived that Obama has reacted badly to the storm, that could hurt him in swing states. Same goes for perception that he did good.
Whether he does good or bad, there is going to be a disaster to react to. If Romney can spin it so that Obama looks bad or Obama so that he looks good, it could be a factor.
Besides, Virginia is close and there is going to be not just an effect there but an effect in a part of the state that is more Democrat than parts of the state that will be less affected.
Mitt's off to a good start - he doubled down on wanting to dismantle FEMA this morning.
Rasmussen is also a GOP pollster and consultant. The RCP co-founder is an outspoken "Christian conservative" who complains about "media bias". I don't think that this impugns their ability to put aside their personal wishes in formulating their methodology, and I'm not sure why Wang's ability to put aside his biases should be impugned, either. If his polling shows a systematic Democratic bias, then you adjust for it in the same way you adjust for other pollsters' (and other analysts') biases.
Not this morning. Romney's FEMA comments were during a primary debate.
As such, we know they mean nothing to Mitt or his supporters.
By hurt Romney, I mean just barely. But barely in a close election is possibly notable.
Dicks like Gingrich already took care of that for him on Sunday.
I noticed that Obama's 12:45 address was 100% non-political, emphasizing the need to follow the instructions of local officials, and that he deflected the question about the effect of Sandy on the election. I'm sure that this couldn't exactly have pleased the Romney camp.
Same old song...
Why are so many people surprised that when we elect people who spend their entire lives railing against and hating government -- they turn out not to be very good at governing?
Nonsense. Rasmussen, almost alone, weights poll results based on its survey of party ID, which it releases on a daily or near-daily basis all year, every year.
I've mentioned this part of RCP's subjectivity a time or two in the past 24 hours, but I don't believe it's as nefarious as you're implying. I don't believe it's unreasonable at all for RCP not to use one poll that didn't exist in 2008, another that didn't exist in 2010, and a third that not only didn't exist 4 months ago but uses a methodology that's never been used before (RAND). If RCP was using some first-year right-leaning polls but not first-year left-leaning polls, I'd be suspicious, too.
This simply isn't true. If Obama was truly ahead in the national race by 3 points, he'd be well over 300 in the Electoral College predictions. Instead, he's basically ahead by Ohio plus New Hampshire at RCP or Ohio plus Colorado at FiveThirtyEight.
So what were the demographic breakdowns of Rasmussen's latest Ohio poll? As a reminder, you said PPP's latest Ohio poll was biased and unreliable because they provided this information in a PDF instead of in their press release:
So, is Rasmussen's Ohio poll meaningless to you?
Natural disasters are mostly a State & Local Government responsibility, I'm going to be surprised if anyone credits or blames the President unless something extraordinary happens. There is some suggestion that the BLS Jobs Report may be delayed, which may raise eyebrows since the surveys are complete and one would think enough people could be designated as "essential" to wrap it up, especially given that the immediate DC area seems to be doing OK.
Actually, I said PPP buried its unrealistic sample in the PDF, which was true yesterday and remains true today.
If you believe Ohio will be more Dem in 2012 than it was in 2008, that's certainly your right. And if you have information that Rasmussen has been using samples that are even more GOP than 2010, I'd like to see it.
EDIT: Some of Rasmussen's party ID results over the past month actually have shown a more GOP electorate in 2012 than in 2010, but I'm not a subscriber and can't get the full breakdown of how he weights the state-by-state results.
You have frequently referred to Rasmussen's Ohio polling instead. Where is the party ID sample for Rasmussen's latest Ohio poll? Blog post? Press release? Tweet?
I have? Until today, Rasmussen had Obama in the lead in Ohio for months, so I kind of doubt I've been pimping Rasmussen's Ohio results here.
Regardless, as I've said several times now, Rasmussen is a subscriber service, and the internals are behind a paywall. According to a discussion at the Battleground site, the Rasmussen sample was D+2 for today's Ohio poll, but I'm not going to subscribe just to confirm that. I don't know why the media doesn't report Rasmussen's internals; maybe it's by agreement because he's a subscriber-based business. But I can guarantee you that if Rasmussen was using crazy R-leaning samples, someone would have broken the embargo by now.
Well, the RCP average then, which includes Rasmussen.
Seems strange to dismiss a poll as "meaningless" because of its party ID results, then repeatedly tout other polls/averages of which you don't even know the party ID results.
I'm guessing RCP shells out the $35 for Rasmussen's internals. Hell, they might even get comped.
I didn't say PPP itself was meaningless; I said the topline poll results are meaningless without the sample providing context. (And before you mention Rasmussen again, remember: Rasmussen might charge for its poll internals, but we know Rasmussen weights its polls in part based on its party affiliation survey, which it publishes on its site for free on a constant basis.)
I don't think the jobs report matters that much. Everyone's perception of the economy is pretty much baked in at this point.
In addition, the numbers are quite likely to be in a narrow bound between 100 and 200K jobs. Does anyone even notice if the headline unemployment rate drops to 7.7%? I mean, of the likely scenarios, where we have no change in UErate, minor drop in UErate or minor raise in UErate, do any of those matter?
It's not like UE is going over 9 or under 7.
It already has!
(Just having some fun with Shipman.)
Thanks, but I didn't bother checking either, until the fifth or sixth time the stat was cited. Sloth is my go-to deadly sin.
Where did you get your numbers? Your findings are at odds with this chart.
Your list and the chart are comparing two different things. Your list is a comparison of the percentages, while the chart is a comparison of margin of victory. In the latter, the +2.0 claim holds up:
- In 2008, Obama won by 7.2 but only won Ohio by 4.6 (GOP +2.6);
- In 2004, Bush won by 2.4 but only won Ohio by 2.1 (GOP -0.3);
- In 2000, Bush lost the popular vote by -0.5 but won Ohio by 3.5 (GOP +4.0);
- In 1996, Clinton won by 8.5 but only won Ohio by 6.3 (GOP +2.2);
- In 1992, Clinton won by 5.5 but only won Ohio by 1.8 (GOP +3.7);
- In 1988, Bush by 7.7 but won Ohio by 10.8 (GOP +3.1).
This isn't how I'd previously seen it presented around the internet and it's less compelling than the percentage comparison, but it still suggests the GOP tends to outperform in Ohio.
I'd say Sam Wang is out on a limb that's hanging over thin ice that's about 15 feet from Niagara Falls. He's turning "out on a limb" into performance art.
Obviously there are multiple ways to turn and present data. But you were talking about how GOP candidates have traditionally overperformed in Ohio relative to the national popular vote. Addressing that premise, what's more germane than directly comparing how the candidates performed in Ohio to how they performed in the national popular vote?
I agree. That's why I said:
... I.e., the straight comparison of percentages is more compelling than the margin-of-victory comparison in the chart I linked.
And the very best part is that Ohio's +GOP factor is small but consistent, which gives every partisan out there one adjective to have faith in, and one adjective to totally dismiss. And vice versa!
As I read the thread (and I keep up with it pretty well), your main criticism of Nate/538 was that it failed to account for the purported 2-point GOP advantage in Ohio, relative to the national vote.
Now that Gonfalon Bubble has debunked that myth, and you yourself have admitted that comparing the Ohio numbers to the national vote are the "more compelling" way to analyze the numbers, do you think that Nate's percentage (a) in Ohio and (b) for the general are accurate?
For the record, in terms of your repeated reliance on the 2-point myth, here is but a sampling:
This was you in 4901: Wrong.
Here you were in 4917: Wrong again.
And in 4966: Wrong again.
Extend an olive branch to the lefties, and they want the whole tree.
To answer your question: No.
It's not a myth that the GOP overperforms in Ohio relative to the national result. The GOP overperforms by less in a straight percentage-to-percentage comparison, which is how the +2.0 thing has been conflated around the internet recently, but the trend in #5553 is still noteworthy.
Getting back to your question, despite a history of the GOP overperforming in Ohio both in terms of percentage and relative to the margin of victory, Nate is still projecting Obama will win Ohio by a wider margin than he'll win the popular vote. This remains unexplained.
We're told over and over and over again that the genius of Nate's model is that he regresses polling data to the historical mean, but he doesn't seem to be doing that in Ohio, or to the extent he is, he must only be doing so after plugging in a lot of pro-Obama data into the model and/or making a lot of pro-Obama assumptions in his modeling. Nate has Obama as a 3:1 favorite for reelection despite a horrible economy, high unemployment, sub-50 approval ratings, horrendous right-track/wrong-track numbers, Romney leading in the RCP, and the fact that incumbent presidents generally either outperform their first election or lose — all, apparently, on the basis of Obama leading in Ohio by 2 points. The idea that a 2-point Obama lead in Ohio polling not only trumps all of the preceding negatives but makes Obama a 3:1 favorite seems both incredibly optimistic and entirely unexplained.
Is that not how you were presenting it in 4901, 4917, and 4966 (and other places)?
So now it is your position that because the GOP outperforms the national *margin,* in Ohio, Nate's model must be wrong? Maybe that is right, but that wasn't your criticism before. Your criticism before was that the GOP outperforms the national vote by 2%. That assertion is incorrect.
Do you think Nate's model doesn't account for all the factors listed above? Do you have any evidence that it does not? Aren't all of those things baked into the polling - Nate's primary data points? If you'd argue that they aren't, how so? As MCoA points out, Nate has written extensively about his methodology, and is hardly running a black box. There are numerous posts in this thread that touch on his methodology. Yet you keep asserting variants of your statement above - that his current projection is "entirely unexplained." This assertion has no basis in fact. His prediction is in line with the other predictions I've seen - a close popular vote with an Obama victory in the EC.
Did you not see my comment, which I'm now posting for the third time, that "[t]his isn't how I'd previously seen it presented around the internet"?
The +2.0 apparently was off, but the GOP still overperforms in Ohio. It simply overperforms less than was thought, at least by that one measure.
Nate's model, meanwhile, is projecting Romney to underperform in Ohio, not only in the face of decades of electoral history, but coming on the heels of a huge 2010 for the GOP in Ohio.
If you claim to be regressing to the mean, but your model projects something that has never happened before, then you aren't regressing to the mean.
He's a favorite because the opposition has proved itself so unpalatable that despite the significant advantages you cite, they are losing anyway.
(note: the numbers I'm quoting are from Nate's 10/28/12 update)
Nate shows Ohio's polling average as Obama +2.8, an adjusted polling average of Obama +2.4, "State fundamentals" as Romney +1.1, and an overall both now-cast and final projection of Obama +2.2. Moving from +2.8 to +2.2 on the basis of Ohio having pro-Romney fundamentals would seem to be a fairly textbook example of regression to the mean.
It depends on how you define "losing." Last time I checked, Romney was +1.5 at RCP in national polls conducted over the past week, +5 at Gallup, and +2 at Rasmussen. The only place Romney seems to be "losing" is in one state where the polls seem to be out of whack, both due to the samples being used and due to people lying about having voted early.
***
Perhaps, but even with that adjustment, he's still projecting Romney will underperform in Ohio.
The general unpalatability of the opposition may be the explanation (or an explanation) for the aggregation of state-by-state poll number being what they are. Or it may not. In any case, Nate Silver doesn't need to offer an explanation, and doesn't pretend to have a compelling explanation. He isn't a pundit pushing a theory about who will win. He's an analyst presenting a model that aggregates state-by-state poll numbers.
He's also, quite clearly, a messenger being shot at.
Most of those (all but "Romney leading in the RCP") are things that Nate's model explicitly does not look at. If poll-aggregating can lead to accurate predictions, it has to be by looking only at the polls. If you want to construct a prediction system that relies on economic trends, feel free. But I don't think it's fair to criticize Nate Silver for not doing that. Things like "incumbent presidents generally either outperform their first election or lose" are outside the scope of the project.
I don't see any mention of it on his methodology page, but Nate has repeatedly mentioned that economic data is factored into his model.
EDIT: Here we go: Measuring the Effect of the Economy on Elections
Such as the already discussed (read: mocked) the University of Colorado forecaster that does that and against all odds has Romney winning Minnesota and New Mexico.
Or Nate's.
Huh. Okay, I retract my comment. Well, the first half, anyway; I still think "incumbent presidents generally either outperform their first election or lose" is too vague to plug into a model.
I'm not sure if or how Nate could plug that into his model, although perhaps it's possible somehow. I was mostly just running off a list of the major things that represent historical headwinds for Obama.
If an analyst lacks an understanding of the 'why', he ends up doing silly things like projecting Matt Wieters to be the best player in baseball after a nice season at AA. People who do nothing more than symbol pushing work at a significant disadvantage to those pundits.
That said, the 'X generally happens in an election' stuff was already satisfactorily smacked down by the xkcd link.
Unlike the University of Colorado's model, Nate Silver's model is neither built on economic trends nor predicts Romney to win NM or MN. But yeah, other than that they are exactly the same.
Swing and a miss.
Your mocking reply to the quote in #5570 suggested you were unaware that Nate's model indeed partly "relies on economic trends," and that you had perhaps missed the link in #5569. Either way, not a big deal.
I apologize for assuming that you understand there is a difference between "includes" and "based on."
Since neither the word "includes" nor the phrase "based on" was used in this discussion, your condescending tone is, as usual, quite bizarre.
The quote to which you replied in #5570 said "relies on," and Nate's model indeed relies in part on economic trends. If you had already seen the link in #5569, then I'm sorry for making you read the two words in #5571.
Do you really think it will end then? There will be the discussions of why the polls/538/other aggregators did/didn't work.
It's only really a shitstorm if Romney wins. If Obama wins, then everything's pretty normal. A Romney win, in addition to being horrible for the country, would also set back the understanding of statistics.
That's better
"People ask me what I do in winter when there's no baseball. I'll tell you what I do. I go on the computer and argue with liberals." — Rogers Hornsby
At least the damned political ads on TV will stop, they are harder to avoid than the polls, IMHO. I would say that 90-95% of the local ads on TV here for the past several weeks have been political. Not so much the presidential election but Indiana governor, U.S. senator and the House. I don't know which are worse, the ads from the candidates themselves or the ones from the PAC's, which of course are completely independent from any of the politicians in the races.
That article is insane.
Those right-wing hacks are just fooling with the narrative.
You can't handle the truth.
Montana? Man, I know those western states all look alike, but still....
Montana? Man, I know those western states all look alike, but still....
Correction, Andy: All white states look alike. Yes, it was supposed to say Minnesota.
Put it all together and I'd say trailing by only 6 points probably isn't really doom and gloom for Obama. It might even be a sign that Obama is doing pretty good all things considered.
You must be Registered and Logged In to post comments.
<< Back to main