Wygart has a comment in over at Pielke the Younger’s blog on his recent post Parlor Games and Predicting Presidential Elections in which he discusses an article by Nate Silver at the NY Times on the ability of political scientists to predict elections based upon measurements of various [mostly economic] “fundamentals”
Can political scientists “predict winners and losers with amazing accuracy long before the campaigns start”?
And his answer
The answer to this question, at least since 1992, has been emphatically not. Some of their forecasts have been better than others, but their track record as a whole is very poor.
And the models that claim to be able to predict elections based solely on the fundamentals — that is, without looking to horse-race factors like polls or approval ratings — have done especially badly. Many of these models claim to explain as much as 90 percent of the variance in election outcomes without looking at a single poll. In practice, they have had almost literally no predictive power, whether looked at individually or averaged together.
Pielke the younger says:
And he goes on, in his usual inimitable way, to dissects the issue, establishes the parameters of what a ‘skillful’ model would have to accomplish in order to prove its, er, skillfulness, how modelers fool themselves and others into thinking that their pet model has some skill, and then lays out the actual track record – not good.
Wygart, in his own unique way, cuts to the quick:
Having been cognizant of every US Presidential election campaign since 1972, I have become convinced that the process is almost entirely irrational [however rational we may be as individuals]. How anyone could suppose that the outcome of a completely irrational process can be predicted on the basis of some “fundamental” process I don’t know.
If predictions based upon various fundamental processes were possible it would have to be because these “fundamentals” actually cause the election result in some real way. By what mechanism could: Housing Starts, the Prime Rate, Unemployment Rate, & etc [however artfully massaged] cause a particular candidate’s success? How?
Think about it for a moment, suppose the Prime Rate really did cause particular candidates to win or lose elections and so to prevent unfair advantage to candidate X or Y news of the Prime Rate was kept from the public to keep elections fair. Would the Prime Rate still have its [magic] effect upon the electorate? – or – would we see that it is the news of the Prime Rate fed very artfully to the electorate through that mass psychogenic illness inducing ‘process’ known as the news media that ’causes’ the magical electoral effect?
My opinion is that these predictive models are nothing more than very sophistry-cated random number generators. Someone with more math skills than me could probably demonstrate this mathematically [if we had the code].
I would tend to prefer the prognostication of a psychic octopus before one of these so-called models.
I will amplify Wygart’s argument by pointing out that underlying the notion that numerical models can predict the outcome a process that resembles mass hysteria there is flawed and shoddy thinking and there is a breakdown in the understanding of cause and effect, namely how so-called “fundamentals” or the news of these fundamentals [and which is it?] effects voter behavior at the polls.
Numerical models such as the general circulation models used to simulate the behavior of the Earth’s climate system depend upon the two notions that, a) certain “fundamental” parameters such as concentrations of greenhouse gasses & etc. are controlled by identifiable natural laws to produce an effect, namely a change in the climate system, and b) that such fundamental processes can be parameterized in the form of mathematical equations that can simulate the behavior of that system to some useful end. The skill of a GCM at simulating the climate system is based upon how successfully the model builder is able to parameterize these “fundamental” processes, how correct his understanding of the relevant natural laws is, and how good his data is.
The whole project of building numerical models rests upon the notion that there are identifiable natural laws in the first place. When it comes to the psychology of human beings: political, social or otherwise, on the scale of the individual or of societies there are no identifiable laws – none, nada, zip – therefore all that is actually possible for these political prognosticators to be doing is an advanced sort of mathematical correlation matching.
What in effect these politico-predictive models seem to actually do is nothing more than parameterize an iIllusory correlation bias. In the end what makes these so-called models as appealing as they are [as advanced “parlor games for academics]” is that they produce results which center so close to an average that they can successfully mimic the performances of a psychic cephalopod.