Pages

Jump to bottom

8 comments

1
The Vicious Babushka  Feb 27, 2016 • 6:20:55pm

Without knowing anything about this formula, like what data is being used and what calculations does he use to arrive at this conclusion, I am inclined to say that it’s bullshit.

If it’s not bullshit, it is the scariest thing that I can think of.

Canada is 20 minutes away.

2
calochortus  Feb 27, 2016 • 6:33:32pm

How long has this model been around? Obviously, unless Norpoth is the worlds oldest living statistician, he didn’t predict the 1912 election in advance.
So that leads me to wonder if he developed a model last month which fits almost all elections in the last hundred years. It seems to me this would have very little predictive value.

3
Charles Johnson  Feb 27, 2016 • 7:55:15pm

Predicting elections that have already happened? Seriously? I’m gonna have to go with “nope.”

4
Big Beautiful Door  Feb 28, 2016 • 5:11:55am

re: #2 calochortus

How long has this model been around? Obviously, unless Norpoth is the worlds oldest living statistician, he didn’t predict the 1912 election in advance.
So that leads me to wonder if he developed a model last month which fits almost all elections in the last hundred years. It seems to me this would have very little predictive value.

Its a process call overfitting. You identify random factoids common to several past elections, then claim you can “predict” future ones. Its bullshit. The so-called pattern making it less likely that the incumbent party will win after two consecutive terms is also bullshit. In reality since the 20th Century a new candidate running for president after his party has held the office in the prior two terms has about a 50% chance of winning, as I’ll demonstrate right now:
Winners: 1904, 1908, 1928, 1948, 1988, 2000*(won popular vote)
Losers: 1920, 1952, 1960, 1968, 1976, 2008

P.S. Note also the circumstances of some of those losses. In 1968 the Democratic Party was tearing itself apart over Vietnam, 1976 was in the aftermath of Watergate and you know about 2008.

5
Skip Intro  Feb 28, 2016 • 8:24:46am

What I take away from this is that the Dems bettter bust their asses getting out the vote. Assuming Trump is going to be a pushover is a huge mistake.

6
b_sharp  Feb 29, 2016 • 6:44:02am

.

7
b_sharp  Feb 29, 2016 • 6:47:16am

re: #6 b_sharp

Climate models use historical predicting to test the accuracy for predicting what will happen, so it isn’t unheard of. However, climate models don’t rely on a single model or run, a model is run multiple times to increase statistical accuracy & then 20 some models are averaged out to get a better margin of error.

If all he’s done is run it against historical events then it can’t be said to be perfect because it hasn’t predicted anything successfully yet and it may be his success in predicting is due to how he set up his constants (see comment #4).

It’s interesting that the RW is jumping on the band wagon for a model that has only historical prediction successes because it supports their political candidate yet reject all of the climate models which have a history of successful predictions & historical predictions.

8
cinesimon  Feb 29, 2016 • 1:02:44pm

It may be ‘historical prediction’, but that model certainly seems to leave out a hell of a lot of context. Climate models of course don’t have to worry about the public’s opinion regarding certain wars, or certain behaviors of certain politicians, or the fact that the electorate changed during the 1960s - then the massive change in political parties after that not to mention the huge cultural/political attitude changes amongst the electorate - etc etc etc… climate models don’t need to take that into account. Political models must - if they don’t, they’re nothing but a gimmick. Maybe he’s looking for funding. Or maybe he’s looking for work in the election. It reminds me of the cliche ‘as goes (insert state/electorate/pundit/group or ‘class’ of people), goes the country’. As was said above, it’s bullshit.


This page has been archived.
Comments are closed.

Jump to top

Create a PageThis is the LGF Pages posting bookmarklet. To use it, drag this button to your browser's bookmark bar, and title it 'LGF Pages' (or whatever you like). Then browse to a site you want to post, select some text on the page to use for a quote, click the bookmarklet, and the Pages posting window will appear with the title, text, and any embedded video or audio files already filled in, ready to go.
Or... you can just click this button to open the Pages posting window right away.
Last updated: 2023-04-04 11:11 am PDT
LGF User's Guide RSS Feeds

Help support Little Green Footballs!

Subscribe now for ad-free access!Register and sign in to a free LGF account before subscribing, and your ad-free access will be automatically enabled.

Donate with
PayPal
Cash.app
Recent PagesClick to refresh
The Pandemic Cost 7 Million Lives, but Talks to Prevent a Repeat Stall In late 2021, as the world reeled from the arrival of the highly contagious omicron variant of the coronavirus, representatives of almost 200 countries met - some online, some in-person in Geneva - hoping to forestall a future worldwide ...
Cheechako
3 days ago
Views: 121 • Comments: 0 • Rating: 1
Texas County at Center of Border Fight Is Overwhelmed by Migrant Deaths EAGLE PASS, Tex. - The undertaker lighted a cigarette and held it between his latex-gloved fingers as he stood over the bloated body bag lying in the bed of his battered pickup truck. The woman had been fished out ...
Cheechako
2 weeks ago
Views: 283 • Comments: 0 • Rating: 1