Senin, 09 Januari 2012

Prognostication #2:The New Hampshire Primary - UPDATE Tuesday morning for Nate Silver's final picks

 It's a Monday before a primary, so it's time for Matty Boy to polish off the crystal ball and make his prediction for the percentages for each of the candidates running for the Republican nomination in the New Hampshire primary. Michele Bachmann dropped out, so it becomes slightly easier, but it is still wild and wooly and no walk in the park.

In previous elections, I would check out the most recent polls and find the median, but that's tricky to do when six people are still in the race. I also have new fun toy, the tracking poll.  The main reason most prognostications in Iowa sucked so bad was that no poll showed Santorum way over 20%, but many did show his stock was rising.  The Suffolk tracking polls shows Huntsman's stock is rising steadily, while Romney has been losing nearly four percentage points a day. So what I did is average out the trends over the past three days and take that trend poll as one of my data sets and the most recent poll that wasn't a trend poll as the other data sets.  I scrubbed out the None of the Above - at least to an extent - and these are my numbers. I also look at the raw data and noted that Buddy Roemer is out-polling Rick Perry in the Granite State and too that into account.  Nate Silver's latest picks are in parentheses. Unless he mentions Roemer in a later tweet, I'm going to be a sport and put his None of the Above numbers on Roemer.

First: Mitt Romney 35.6% (38.5%)
Second: Ron Paul 21.3% (18.6%)
Third: Jon Huntsman 16.7% (17.0%)
Fourth: Newt Gingrich 12.8% (11.5%)
Fifth: Rick Santorum 11.2% (12.3%)
Sixth: Buddy Roemer 1.3% (0.9%)
Seventh: Rick Perry 1.1% (1.2%)

Nate numbers are final on Tuesday morning.  Currently, he's bullish on Mitt, Santorum, Huntsman and Perry. I expect over-achieving by Ron Paul, Newt Gingrich and now Buddy Roemer. I readily admit I can't be sure about the Gingrich-Santorum struggle for fourth and fifth.  All my indicators favor Newt, but I'm just a blogger in my living room and Nate Silver works for the New York Times.

Still, if he gives me a call and wants to put money on this, I will take his bet.  Eagerly.

Wednesday morning I will give the results. I beat Silver by the narrowest margin in Iowa when rounding to the nearest tenth of a percent, 83.8% to 83.7%. I expect we will be closer to 90% if not over this time.

A crazy poll tracking the crazy Republicans.

CBS News national poll - mid September 2011 to early January 2012

All polls have to be taken with a grain of salt, but some of them need a whole salt lick. Here is the tracking of the remaining Republican candidates in the CBS News national polls. They have a survey roughly once a month and the numbers show some well documented trends. Rick Perry is in red (for embarrassment) and you can see his steep early slide. Gingrich is in grey (for the color of his hair and the age of his ideas) and you can see his rise in December and fall in January. Santorum is a muddy brown (I'll let you guess why) and we see his big bump in January. Paul in gold (for the gold standard) has gone from 5% to 10% and Huntsman in orange (no reason, it was just a color left over) stays firmly at the bottom of the pack.

And then we have black and blue, which stand for Someone Else and Undecided, respectively.  These colors were chosen because they are beating up the field. Undecided is fading as should be expected, but it is still well over 10%, dominating Ron Paul and the second tier candidates. Someone Else, on the other hand, continues to poll strongly.

Here's the thing.  The supporters of Cain and Bachmann in earlier polls would now be lumped together as Someone Else, which should inflate those numbers somewhat. (By the first survey in September, Trump and Pawlenty were already just footnotes.) From December to January, Someone Else has lost no strength at all and is tied with Mitt Romney in green (for lots of money) for the lead.

Non news flash: There is no Someone Else! Sorry, Republicans, the ghost of Reagan or the return of Jebus are not on the ballot and the paperwork to get them there is a serious bitch.

As I stated earlier, a grain of salt is not a bad idea in this case. Compared to Gallup's daily tracking, several numbers seem out of date or just plain whack. Even so, if the one-two punch of Someone Else and Undecided are still soaking up a third of Republican voters, that would put Obama's alleged enthusiasm gap to shame.

(p.s.  My New Hampshire prediction and the comparison to Nate Silver's numbers will be published later today.)

Minggu, 08 Januari 2012

One last look at December.

Gallup national tracking polls for December
The month began with Gingrich the Grey proclaiming "I am the nominee" and ended with him making a pact to be Rick Santorum's wingman. Only Romney - shown in green to signify all the cash that's behind him - is currently polling better than None Of The Above.  You'd think that would make his nomination nearly inevitable,  but it shows a deep dissatisfaction in the Republican electorate that might still become a coalition. As we will see on Tuesday, Romney is inevitable in New Hampshire, but as the primaries move to the South, things could yet turn strange.

Kamis, 05 Januari 2012

Why the press hates New Hampshire.

The political press had a field day in Iowa because Iowa gave them the things they like.  They had something new (the Santorum surge), they had a close race and they had controversy. This GOP field almost guarantees controversy - the 11th Commandment of "Thou shalt attack no other Republican" is as dim a memory as most of the rest of the truth about Reagan has become - and Michele Bachmann quitting will be new for a day or two. But for a close race, New Hampshire ain't it.
Suffolk University is doing a daily tracking poll in the Granite State, the only new polls from anyone in over a week. The numbers are just lying there like some old dead animal. Romney is at 43% as predictably as clockwork and the closest thing to a surge is None Of The Above passing Ron Paul for second place.  This poll was taken before Bachmann quit and Perry tweeted something positive about "on to South Carolina", but that will make little difference to the Republicans of New Hampshire, who had been giving both of those candidates 2% each until Perry slipped on Tuesday to 1%.

Here's the thing.  Romney is currently supported by over 50% of the voters who have made up their mind, since 43/82 is about 52%.  50% of the vote in a six person race is a good old fashioned ass whuppin'. There's no way to spin "we finished second" into anything like good news. 
The strength of None Of The Above this close to the election is startling.  I think a lot of those people are going to stay home. Back when I was a lad, Doonesbury would have several weeks of New Hampshire campaigning strips in the December before a presidential election, but being a political junkie now means getting a steady stream of Iowa news before Christmas and barely a week of New Hampshire stories before their little election is over and done.  Given that old people vote in larger percentages than the young, None Of The Above looks like a symptom of the New Hampshire voters' depression over no longer being the prettiest girl at the dance.

Let me scrunch together all the enthusiasm I can muster over the race for second place.  Okay.  Now that I see it in a nice neat pile, that's not a lot of enthusiasm.

Let me state the obvious.  Romney will be in first and Perry will be in sixth. I expect the few Bachmann voters in New Hampshire will throw their puny weight to Santorum, as will some of None Of The Above. This was supposed to be the state where Huntsman was going to finally make a showing over 10%, and while that is a possibility, he is going to be hard pressed to beat Paul or Santorum now. That means Gingrich and Huntsman are scrapping for fourth place. Newt might go higher, but the trend line is definitely down for him everywhere, as it has been since early December. That would say the top three finishers in New Hampshire might well be the same as Iowa, but this time with Romney far and away in the lead and the fight between Paul and Santorum being close.
We will see if any of the polls in the next four days put an exciting spin on these numbers, but really, when the guy in first is outpolling the next five guys combined, "exciting" really isn't an option.


Rabu, 04 Januari 2012

You know who I miss? Ugg the Repug.

 Talking Points Memo, the left wing political news website, has shut down comments for the time being on all their stories.  The place was hit hard by Ron Paul supporters (known to conservative detractors as Paultards and to progressive detractors as Ronulans) and for a while in December, all Ron Paul threads were comment free.  Sadly, they have decided to shut down comments on all threads now, which means I will not get to hear from several clever commenters.

Easily one of my favorites is Ugg the Repug, a fellow who pretends to be a caveman pretending to be a Republican. Ugg has a limited understanding of English grammar but a finely tuned sense of humor.  He laughs at his own jokes from time to time (Har har har!), but his jokes are funny with or without the Internet laugh track.

One can only hope the website will bring comments back as soon as possible.  In my travels around the web, only the comment section on Princess Sparkle Pony is as much fun.

Results for the first prognostication:Not so good.


I picked the order Paul, Romney, Santorum at the top of the Iowa Caucuses.  It actually came out Romney and Santorum in a near dead heat for first and Paul many percentage points behind. I got the order of the also rans right, but missed their percentages.  Let's go through the wreckage candidate by candidate.

1st place: Mitt Romney 24.6% 
My prediction of 22% was off by 2.6%.

2nd place: Rick Santorum 24.5% 
I predicted 19%, my big screw-up of the evening.  I lose 5.5%.

3rd place: Ron Paul 21.4% 
I was 1.6% too high with 23%. 

4th place: Newt Gingrich 13.3% 
Too high at 15%. I lose 1.7%

5th place: Rick Perry 10.3% 
Much closer.  Off by 0.3%

6th place: Michele Bachmann 5% 
Once again, two points too high at 7%. 

7th place: Jon Huntsman 0.6% 
I thought he'd get about 3%.  I overestimated the sanity of the Iowa caucus goer. I lose 2.4%

Others: 0.3% 
I said 1%.  Take the 3% I over-estimated Huntsman and the low end choices and give it to Romney.

What grade do I deserve?  If we accumulate the percentage mistakes I made, I get an 83.9%, which I would call a B.  I think that's a grade I can live with.
As for the places, There are eight positions, so if we say the basic adjustment is to switch two adjacent places, like second and third trading places, It would take sixteen such transpositions to go from completely backwards to correct.  To make my list right, I need to switch Paul with Romney for the top spot, then switch Paul from second to third with Santorum. 14 right out of 16 would be 87.5%, about on the cusp of B and B+.

Of the two grading systems, I think the accumulated percentage mistakes is the fairest.  As people drop out, getting the correct order of finish will get easier, though when it gets down to two candidates, then it becomes pass/fail.

So, unlike many other prognosticators, I will keep track of my grades.  Could we lose a couple candidates soon?  Signs point to yes. Perry slunk back off to Texas last evening, for example, and reality might even seep through Michele Bachmann's caked on make-up, touching the virgin territory of her brain.  Every person who leaves the race makes my job slightly easier.

And just to make myself feel a little better, I took the last seven polls taken in Iowa, adjusted the "None of the Above" down to zero, increased all the other percentages proportionally and took their grades on the caucuses. Here are the names of the companies, the date of the polls and their grades.

Rasmussen(12/28): 82%
NBC News/Marist (12/27-28): 81%
Des Moines Register (12/27-30): 81%
PPP (12/31-1/1): 80%
We Ask America (12/29): 74%
ARG (12/29-1/1): 68%
Insider Advantage (1/1): 62%

As you can see, polling as close to the actual date wasn't much help.  Insider Advantage flat out sucked asking people on New Year's Day, while Rasmussen did the best when they packed up their tent on December 28.  Everybody underestimated Santorum.

My next prediction will be next Monday before New Hampshire votes on Tuesday.

Senin, 02 Januari 2012

Prognostication #1 for 2012: The Iowa caucus

Okay, Matty Boy has been crunching the numbers and is ready to predict the Iowa caucuses being held tomorrow. I will also come back on Wednesday to show how brilliantly I did or how badly I sucked.


1st place: Ron Paul 23%
2nd place: Mitt Romney 22%
3rd place: Rick Santorum 19%
4th place: Newt Gingrich 15%
5th place: Rick Perry 10%
6th place: Michele Bachmann 7%
7th place: Jon Huntsman 3%
Others: 1%

This will officially start the Santorum Surge. It will be another bubble. Gingrich's time in the sun is going to be hard to hold onto if he finishes fourth (or worse) here are gets pounded in New Hampshire, which are the likely outcomes.  I thought he peaked at the right time in December, but I did not anticipate just how strong the animus towards him would be from so many quarters and how much money they were willing to spend to neutralize him.

Overall, I think Romney is the nominee.  Some polls have shown people's second choice candidates, and Romney is doing better as a second choice than I thought he would. The one power player who still hates Romney is Rush Limbaugh, but he has been known to take 180° turns in the past. I can't predict there will be a third party candidate who can pick up 10% or more of the vote, but if there is, it favors Obama.

Of course, all that is long range crystal ball stuff.  Back on Wednesday to crow from the rooftops or to eat crow. If you want to follow me on Twitter, I'm @ConfidenceOfVic, short for Confidence of Victory, the name I gave my statistical method that can be used in races with two or three main candidates.