Posts Tagged ‘aimless speculation’

Dow Jones up 500 Points on News that the Yankees have Acquired Nick Swisher

November 14, 2008

Well, perhaps that had nothing to do with it. I find it very difficult to say with any certainty why the market behaves as it does over a short period of time. This puts me in the minority. The WSJ, for instance, recently ran an editorial laying out a theory already popular with many of our friends at the Corner:

No President-elect in the postwar era has been greeted with a more audible hiss from Wall Street. The Dow has lost 1,342 points, or about 14%, since the election, with the S&P 500 and Nasdaq hitting similar skids. The Dow fell another 4.7% yesterday.

But there’s little doubt that uncertainty, and some fear, over Barack Obama’s economic agenda is also contributing to the downdraft.

Little doubt? Jonathan Chait seems to have quite a lot of doubt, gloating as the Dow soared today. No doubt Chait is largely joking, but there have certainly been plenty of lefties giving Obama credit for every silver lining they can find in the dark economic clouds, while sub-prime morgages are rapidly being reduced to a minor contributing factor in the conservative account of the financial crisis Obama has brought down on all of our heads.

These bits of market analysis are absurd, but no more so than what we hear about the markets every day of the year. People are up in arms over attributing market gains or losses to Obama beacuse a new president-elect is something about which people get up in arms, not because those attributions are any less grounded than usual. Headlines following the same formula as the one above this post are a regular feature of the daily news. But the idea that the day’s trading can usefully be explained as the effect of a simply stated cause immediately obvious to reporters is ludicrous. It’s probably true that, from time to time, some easily observed event occurs whose effect on the market is sufficiently dramatic to make all other factors relatively uninteresting in accounting for market movement over a very short period, but, for the most part, media outlets are simply looking at whether the markets did well or poorly, then running with the most recent news event that seems most conducive to that outcome, and voila. There may be some utility to this sort of analysis, but the ubiquitous practice of presenting it as fact (in headlines!) is unfortunate.


Predicting the Outcome, Part II

September 26, 2008

While a lot has happened in the polls since the first installment of my forray into election projections, I’m going to ignore actual polling data for now and focus on potential systematic problems with polling in general. When a pollster says that its latest data on the election has an x point margin of error, they are, funnily enough, not claiming that the numbers they are giving you are within x points of the actual percentages of voters who would have voted for each candidate if the election had been held on the day of the poll. Instead, they are claiming that, assuming their sample was truly random, there is a (usually) 95% that their figures are within x points of the figures you would get if you asked everybody. The advantage of making this latter determination is that it’s possible to do so. (In fact, it’s easy. Give it a whirl.) The major disadvantage is that the initial assumption – that any member of the population in question is equally likely to be polled – is doing quite a bit of work here, despite the fact that absolutely everyone knows it to be false. The hope is that groups that aren’t so big, holding views that aren’t so different from those of the population at large, are being underpolled by not so great a margin as to make the results all that much less accurate than they purport to be.

All of which is a long way of saying that there are factors that could be screwing up polling data. Here are some candidates:

Read the rest of this entry »

Obama Not Headed for Mt. Rushmore after all

September 22, 2008

Or is that South Dakota? In any case, Ben Smith reports that the Obama campaign is pulling out of North Dakota:

This is the third state that appears to have come off the table since Obama’s campaign laid out an ambitious 18-state battlefield. His campaign also pulled out of Georgia, and Sarah Palin’s nomination appears to have put Alaska out of reach.

At a briefing for reporters in June, Obama campaign manager David Plouffe recognized that the battlefield wouldn’t remain that wide to the end.

“We have a lot of differing combinations to get to 270, and our strategic imperative is going to be … to keep as many of those scenarios as possible alive” deep into October, he said.

Over the next 40 days, other states will likely come out of play; the question is how long some of those, from huge ones like Florida to marginal Montana, remain on the table, as well as how competitive McCain can keep his own forays into the Kerry states, in Wisconsin, Michigan, and New Hampshire.

In the first installment of my own forray into the projection game, I didn’t include North Dakota, Georgia, Alaska, Wisconsin, or Montana in my list of states in play. I agree that Florida is going to be tough for Obama, but I think it merits inclusion. The most hotly contested state I didn’t list is North Carolina. With a new poll out showing the race tied there, I would include it if I were writing that post today, but, as Nate Silver points out, North Carolina is still unlikely to be a decisive state, since it is extremely unlikely that Obama could win there without also winning Virginia, in which case Obama would only need one of New Hampshire, New Mexico, Nevada, Colorado, Ohio, Michigan, or Florida. Silver adds the proviso that it could become relevant if Obama were to lose Pennsylvania, but I still don’t consider PA a true swing-state.

More speculation will follow soon.

UPDATE 9/23 12:24 PM: Based on today’s polls, I’m going to give up and concede that PA is in play, although it’s been a long time since McCain lead there in a single poll not conducted by Zogby, which is not exactly a credible source. As discussed above, this makes North Carolina somewhat more relevant – another poll shows the race tied there. Finally, though it’s still more interesting than most states, New Mexico is pretty safe Obama country now, and shouldn’t be on the short list of swing states.

Predicting the Outcome, Part I

September 19, 2008

The fine folks over at fivethirtyeight don’t have a lot of good news for John McCain. According to their model, yesterdays polls sent Obama’s chances of winning the electoral college vote soaring from 45% to 61.2%. As was discussed yesterday, no rational observer would actually have taken that first number to heart; McCain’s polling numbers have been propped up by a convention bounce, the disappearence of which one should have predicted – as fivethirtyeight in fact did. As ugly as the current numbers are for the GOP, there is reason to think the reality is grimmer still.

The polls just introduced to the model are the first to take into account Obama’s post-convention-bounce upswing. Obviously not every state has been polled as recently as every other. One of the things that makes fivethirtyeight’s model so good is that it partially makes up for this by extracting national trends from new polling data and applying it to states that haven’t been polled as recently based on their demographics. But (as I understand it) real polls are weighed more heavily than such projections, so which states have the most recent data matters.

As with any presidential election, there is a short list of states we are actually interested in. Polling shifts in New York, Texas, or California will only affect the overall projection insofar as they indicate national trends which are applied to projections for other states, whereas polls in swing states contain valuable information in and of themselves. Since polls in swing states will thus have a larger effect on the model, large national swings will be under-accounted for until these states are polled.

Here’s a likely electoral map, with the most closely-contested states left blank:

So if things are moving in Obama’s favor nationwide (as one would expect as an unfavorable convention bounce fades), that fact will only be fully taken into account by the model once there is good polling data from Nevada, Colorado, New Mexico, Michigan, Ohio, Virginia, Florida, and New Hampshire. Of the thirty newest polls, twelve concern those states, which at first glance looks pretty good. Six of those polls, however, were actually taken on the 14th or earlier, before Obama’s numbers started to take off (I’m not sure why these polls were added only yesterday with much more recent data). Furthermore, the model weighs polling results based on the historical accuracy of the pollster responsible; only two of these twelve polls were taken by better-than-average sources, and one of those two was taken back on the 15th.

The upshot of all this is that while Obama and McCain have swapped places as the favorite according to the model, McCain’s situation now is nothing like Obama’s was a few days ago. Whereas there was good reason to think McCain would lose the ground he had gained, there is now good reason to think Obama will gain even more ground as the data catches up with a shift that has already occurred.

UPDATE 6:35 PM: I see that while I was writing that post, a new set of data was added to the model, which now puts Obama’s chances of winning at 71.5%. I haven’t looked at the individual polls added yet, but I’ll update again if there’s anything particularly striking.

Also, it’s worth reemphasizing that these ‘percentages’ aren’t really complete predictions, because they rely entirely on polling data. They give a sense of what would be likely to happen if the election took place without any new events affecting voters. If there is available information about things that are likely to happen between now and the election – and there always is – then one’s actual confidence in the outcome of the election should likely diverge from these numbers.

Ambinder’s Politics

September 11, 2008

A quick aside to my colleague here: for the most part, I agree with this post, though I plan to write something on the latest polling myself the next time I’m not busy reading through Alaskan court documents. (Did you know Todd, Track, and Bristol have all been ticketed for speeding? National Inquirer, take note.) But this puzzled me:

Even a post or two of Ambinder’s have a faint whiff of dismay.

One of the neat things about Ambinder is that he keeps his own politics very close to his chest, but the consensus amongst his readers, and those of other Atlantic bloggers, is that he’s probably pretty conservative. Mostly they say this because they are all whiny liberals, many of whom think that Yglesias is a conservative on the strength of his failure to condemn the evils of capitalism. But I tend to agree with them on this point; if I had to guess, I’d say he votes Republican. Obviously, you disagree. What’s your thinking here?

Re: Palin as Rational Choice

September 7, 2008

There can be only the most respectful disagreement between even distant cousins in the ‘the Great’ family, but I must say I’m not convinced by Frederick’s analysis of the Palin pick. The basic insight is a good one: since there is relatively little effective difference between a narrow defeat and a blowout, a strategy can make the latter much more probable and still be rational. Certainly she is a very real risk to become a major liability, and perhaps she also has a shot to be a major boost. But I suspect this hurts McCain’s chances overall, for the following reasons:

1.) I’m don’t see her having quite as much upside as Frederick suggests. As best I can tell, her job is to take over the role of Republican candidate while McCain vies for independents. She is certainly doing a terrific job of thrilling the base, so she could draw out a bigger conservative turnout than McCain could have, but – by becoming the most prominent figure in the race – she might well be making it impossible for McCain to gain much ground with moderates.

2.) That said, I agree that their is at least a non-negligible chance that this strategy provides a major boost to the ticket’s performance, but I still think the graph is misleading, because I see no reason to think that the potential upside is as great or as probable as the potential downside. Given what we already know (the ongoing ethics investigation, another possibly following it, the suspect firings in Wasilla, the improper involvement of Todd Palin in executive matters, the chance that that involvement could lead to damaging emails losing the protection of executive privilege, the possible affair, the Jimmy Hoffa connection, etc.) there is a decent chance that some of her baggage could cause huge damage to the campaign. I don’t see how even the best possible realization of the Palin strategy could match this downside. Furthermore, it is almost certain that some of these scandals will end up doing at least some damage, which means the strategy has some work to do before it can break even.

3.) While it is true that McCain should be (more or less) indifferent between a narrow loss and a landslide, it does not follow that he should be indifferent to different levels of potential harm from a particular decision when both would lead to defeat based on current polling numbers, because none of these decisions exists in a vacuum. That is, when weighing potential VP picks, possible downsides of two points and ten points are not equivalent simply because either would suggest a lost based on where we are now; all sorts of other factors could shift things in McCain’s favor such that he would win with a VP that did nothing for, or even slightly damaged his polling, but still lose with a VP implicated in a major scandal.

4.) Building on this last point, even though McCain had been trailing consistently, treading water would not have been an entirely hopeless strategy, as any number of things could happen to shift things. An Obama scandal could surface; Cheney could start a war with Iran; someone on the Democratic side could commit a hymie-town-level gaffe in a public setting. A McCain campaign barely trailing could capitalize on such an event; a McCain campaign in shambles might not be able to. So while a high risk strategy such as this could certainly be the rational choice, the price has to be right. With Sarah Palin, I don’t think it is.

President Palin

September 5, 2008

There’s a lot of talk these days about Sarah Palin’s qualifications or lack thereof for assuming our nation’s highest office. This is certainly an important discussion to have, but I’d like to leave aside the debate – if it can be characterized as a debate – over whether Palin should be president, and focus on the question of whether Palin will be president. Whatever we think of the former question, it is simply a fact that the governor is now one of the four people most likely to be president, say, three years from now. As there are a great many people who seem to think a Palin presidency would be a disaster, it would be helpful to know just how likely a contingency that is, so they can prepare themselves accordingly – gazing fondly at the Alaskan National Wildlife Refuge in its pristine condition, treating themselves to one last abortion, building a bomb shelter, or in whatever other way they deem appropriate. So let’s kick the ballistics here.

Alex Burns over at Politico, citing Social Security Administration data, claims that for a man of McCain’s age there is “between a 14.2 and 15.1 percent chance of dying before Inauguration Day 2013”. For convenience, I’ll split the difference and call it a 14.65 percent chance. It’s worth noting that this is a pretty crude estimate, as it considers only age and gender. As President, he will have a terrific health plan – and don’t let Obama tell you he can get you the same deal. On the other hand, he’s a cancer survivor and I hear his diet in Vietnam wasn’t very health-conscious. So it might be worth crunching the numbers a little more carefully but, for now, I’ll work with what Burns has given me.

Of course, all that is moot unless McCain is elected. President McCain futures are trading at 43.7 over at Intrade at the moment. It would be a stretch to call guessing about politics an efficient market at this point, but as a rule it’s always better to listen to people who are paid to be right than to people who are paid to say clever and interesting things. As far as I know, Intrade is the best game in town for the former.

Finally, we need to consider the possibility that the governor will go the way of Thomas Eagleton. The market says there is a 5.8 percent chance that she will withdraw before the election.

Now I get to show off my math skills: the probability of Sarah Palin becoming president before the next election is (.437 * (1-.058) * .1465) = .0603 = 6%. (I realize I didn’t account for the possibility that McCain dies in office but only after Palin herself shuffles off this mortal coil, but that would be a fairly minor adjustment.)

So there you have it. If you ran the next four years a hundred times, we’d have six President Palins. It probably won’t happen, but I’d recommend against divorcing any of her family members.