George Rebane
[I've been noodling doing a 'predictions derby' on RR since last summer as potential candidates started making noises about running in 2016, even before the 2014 mid-terms were held. If it worked, then the 'derby' would be held in three parts - who will be the declared candidates going into the conventions, who will be nominated, and who will win in Nov 2016. The output of this exercise would be periodic outputs of bar charts of probabilities (see below) that would be updated as new happenings took place and new evidence came in. Interested readers would evaluate such information that I would then aggregate in a Bayesian update formulation to post the new bar charts.
I have no idea how this will turn out with respect to reader interest and the work to track such political happenings; but since we track and comment on them anyway, I thought summarizing our collective take in an evolving graphical format would be interesting. I wrote the piece below last summer; and you should probably download it if you want to play. Note the bar charts start out at 0.5 probabilities for each potential but undeclared candidate. This shows that before considering evidence, we are 50-50 ignorant about whether they will run or not.]
Ever since Nate Silver became a phenom prognosticator of some renown (The Signal and the Noise), I’ve considered starting a prognostication feature on RR that involves its readership. The methodology will be based on the Bayesian inference techniques on which I have reported before (search RR for ‘Bayes’). While Silver’s book is primarily a self-promotion that claims to explain his methodology but doesn’t, RR readers following my explication of Bayesian inference will be able to develop and use the methodology for countless purposes in their own private and commercial affairs. Look at it as part of the service ;-)
What really tipped my decision to give this a try on RR was twofold – Silver’s disastrous performance at the FIFA World Cup predicting Brazil’s defeat of Germany (at around 0.68), and some ideas for commercial applications. But the already ferocious political maneuvering by both parties preparing candidates for the 2016 elections was the real clincher to motivate the development of a participative predictions process (think of it also as ‘crowd sourcing’ and integration of evidence). So I started to push some squigglies with Bayes theorem and came up with an easily understood formula that should provide some entertainment, and that also has a rigorous decision theoretic basis – that is, it’s not just idle fun.
The idea here is to predict who will run, and then who will be nominated as each party’s presidential candidate. If there is enough interest, I’ll extend the methodology to predict our next president. And all of this will be done by computing and updating our ‘collective’ beliefs about the future. The measure of belief is the probability that something yet unknown will come true. Belief calculations are based on a combination of hard probabilistic data, and subjective assessments all brought together under the celebrated formalism discovered long ago by the good Reverend Bayes (and rediscovered about 50 years ago when the methodology really took off).
So how will it work? Let’s discuss the ‘hat into the ring’ predictions first. We can all come up with a list of potential candidates from each party and add to the list an ‘Other’ candidate. The fundamental Bayes approach takes a prior chance, odds, or probability, and combines it with recent evidence to calculate an updated or posterior chance, odds, or probability that now reflects the latest evidence. The prior probability summarizes all the knowledge we had about each candidate’s propensity to throw their hat in the ring. And incorporating the latest evidence (news report, stump statement, lurid revelation, etc) will yield the updated posterior probability that again incorporates and summarizes all the previous knowledge we have about each candidate in the context of the hypothesis ‘s/he will throw his/her hat in the ring’. You can visualize the result as being a histogram with each bar labeled with a potential candidate’s name and having a height from zero to one. As time goes on, the bars will get taller and shorter, and some may appear while others are removed.
Everyone can bring evidence to the table and give his assessment of that evidence in how it impacts each candidate being tracked. We may debate the assessment as others refute/modify it, but I will be the final arbiter because, well dammit, it’s my blog (so there). But so as not to unreasonably piss off anyone, I will always do my best to found my adjudication. In any case, as opposed to Silver’s close-to-the-chest methodology, here you can refuse to accept the RR prediction and run a parallel one yourself, and show us all up.
[to continue reading this piece Download Predictions Derby]
George, I may be the only regular (besides the host) with a formal education in Bayesian probability, but I don't get the fascination with this application as I think even Fuzzy Logic is too formal for the machinations of Presidential hopefuls a year and a half out from the election.
My druthers... the GOP had better nominate a governor/former governor (preferably, not including Christie, Romney, Perry or Huckabee) to head the ticket, and a bright libertarian Senator (guess who) for VP to give them some experience being closer to the White House before getting a real chance at the job.
My totally delusional druthers... a left-libertarian comes from out of nowhere to lead the Dems back to their anti-Federalist roots. Won't happen, but a guy can dream. I don't think the country can afford another term or two of a delusional, idealistic President whose only management experience was running (or at least having a say in) their first Senate and their first Presidential campaigns. If you are GOP and think there will be a crash, a President Warren to be holding the bag when the country goes up in flames could be an overall positive thing, if the country doesn't descend into a Stalinist trap. With luck, the radical left would completely flee the Democratic Party and a libertarian middle could reemerge to be a major party a'gin.
It's fun to write fiction. Back to making some popcorn, it's going to be a long campaign.
Posted by: Gregory | 03 February 2015 at 12:41 PM
Gregory 1241pm - I admit to being a bit over-hopeful here. But there really is no bottom limit to where Bayesian inference can be applied, and I'll be surprised if RR will be the only website attempting this as a regular feature. I tried to write the tutorial piece in an easy-to-understand manner, and understanding the Bayesian update is not even necessary to assess the likelihood numbers that represent the pieces of evidence as they come dribbling in over the coming months. I hope that the explanations of how the first likelihoods are assessed will get everyone interested on board, and we'll take from there. Otherwise it will be just you and me, and you sound a bit tentative. But I hope the bar graphs will be fun to look at as they change.
Posted by: George Rebane | 03 February 2015 at 01:31 PM
HILLARY 2016 - !
Posted by: fish | 03 February 2015 at 04:15 PM
fish 415pm - Huh?
Posted by: George Rebane | 03 February 2015 at 04:44 PM
I'm hoping the left will finally vote per their stated principles:
http://www.dsausa.org/sanders_petition
The Koch brothers will help finance him, I'm sure!
Personally, I don't care who is president. I'd like Americans to wake up and pay attention. OK - that's delusional too.
Let the games begin!
Posted by: Account Deleted | 03 February 2015 at 06:32 PM
Well - this doesn't bode well. Good going, Millennials!
"That’s right — 77 percent of 18- to 34-year-olds in the new survey could not name even one US senator in their home state."
OK, it's just a survey, but the results don't bode well for the country. If you can't name even one senator from your state, you shouldn't even be voting. But of course, the Dems are counting on this exact kind of demographic. Read it and weep:
http://fusion.net/story/41972/fusion-poll-millennials-politics-hillary-clinton-jeb-bush-election-2016/
Posted by: Account Deleted | 03 February 2015 at 06:49 PM
Yeah Scott, I could give a rats ass which Democrat or Republican becomes President. I'm for Gary Johnson if he runs. Done deal. The rest is just sport. Just follow the TPP and put your bet on those who support it. There is NO WAY the Pubster wing of the fat bird will stray from that allegiance or Hillay for that matter. the "social issues" are meaningless to the big bucksters that run the show for their own profit. No9tice what a low profile the main stram press on both sides give the TPP. Have you ever heard it being discussed on FOX?
Posted by: Paul Emery | 03 February 2015 at 06:52 PM
It's will be an excruciating long time until the outcome is certain. Don't even think it is a matter of who I like at the moment. It's more like who can win the nomination. Then it gets down to who (whether I prefer him or her or not ) can grab the whole enchilada. No one from either side can win without their respective parties' backing and machinery firing on all cyniders.
Paul is right. The Press has displayed unusual adhorment for the Tea Party types. They hate Palin and Cruz especially. Case in point. Just recently Palin gave a talk (before announcing she ain't running). She appeared to muff her words in a sentence and the media went apeshit. "Sarah blabbed incoherently, Palin loses it, Wacky Palin's TelePrompter went down and dumb Palin could not even construct a sentence", etc. they had a field day until someone pointed out she was reading a quote from Dr. Martin Luther King, Jr. Opps, but it is a perfect example showing what a Tea Party Patriot is up against.
Who knows how many wannabes will step in it and whether they can recover from the inevitable flubs, wrong things to say, and bonehead statements. I hope Biden runs, but that is just a conservative wet dream. No, my candidate must win the nomination by his/her own merits and tenacity. So, right now, it's Ben Carson or Rubio, but both have already stepped in the sticky brown stuff recently. In reality, it may well be just another Bush vs Clinton Thang. Boring.
Mr. Scott, in regards to your read 'em and weep, never underestimate the young people in waiting. Some are starting to get it. Hope burns eternal.
http://touch.madamenoire.com/all/508462#1
Posted by: Bill Tozer | 03 February 2015 at 07:31 PM
Posted by: Bill Tozer | 03 February 2015 at 07:31 PM
Yeah Bill....those youngsters oughta show "Snitchy Al" some respect! Brotha gots to make a living now don'ts he?
Posted by: fish | 03 February 2015 at 07:40 PM
"Some are starting to get it"
Some always have. Just never enough. My personal harbinger of hope is Italy. Completely dysfunctional most of the time and when they do get it together they put more commies in charge. Fortunately they are so inept and worthless, they can't even control the population. So everyone just does what they want and somehow it works. Just make sure you pay off the local capo. This nation doesn't even deserve to live under the Constitution any more. May as well just put our hope in doing as well as Italy.
Posted by: Account Deleted | 03 February 2015 at 07:50 PM
Well, at least those young leaders are speaking my language!
Posted by: Bill Tozer | 03 February 2015 at 08:17 PM
ScottO 649pm - I too agree that if you can't name a senator from your state, that is an indication you should stay out of the voting booth - you are either to stupid or disinterested in the process to be sufficiently informed, and are therefore easily swayed by the last thing that is shouted or whispered in your ear. More of my thoughts on voter qualifications were recorded here -
http://rebaneruminations.typepad.com/rebanes_ruminations/2012/12/who-should-not-vote.html
Posted by: George Rebane | 03 February 2015 at 09:15 PM
Poor Sarah the quitter
She was picked to run with McCain when the pubsters decided to throw the fight in 08' She had her brief fling in the big time with Fox before being dumped. I don't feel that bad for her since she made millions as a comic celebrity. The sad thing is that she actually takes herself seriously. By the way whatever happened to the other Pubbers babe Michele what's her name. This stuff is really fun to write about.
Posted by: Paul Emery | 03 February 2015 at 10:54 PM
Oh Paul, you will have much fun with all these unpolished canidates tripping over themselves. Guess with Gary off the radar you won't bother to vote. At least you could arise out of the nose bleed seats and pick a 2nd choice, then continue with much fun. Elizabeth said she ain't taking on Clinton. How about Bobby J? He is yet to step in the sticky Brownless Brown, so not a open target from the peanut gallery. Not as big a target as Christy either. Hey, Bernie is running. Perfect 2nd choice.
Posted by: Bill Tozer | 04 February 2015 at 05:56 AM
A Clinton-Warren ticket would rival the Obama-Uncle Joe juggernaut. No opposition so their war chest would be bustin' at the seams. Done deal. It's over. Maybe they could pick James Carvelle the Ragin' Cajun for The Ministry of Defense. With all those ragin hormones and James's hardball style, we will all be saying "ISIS?, what ever happened to them?"
Posted by: Bill Tozer | 04 February 2015 at 06:18 AM
Great graphs George, very informative.. and you even copyrighted them.. I bet you get involved in dozens of infringement suits as scholars everywhere scramble to use them. LOL!
Posted by: Joe Koyote | 04 February 2015 at 08:42 AM