Loki Liesmith
Loki Liesmith's JournalSo Trump's business model
is basically
1) Get heavily leveraged
2) Force most losses onto other parties
3) Claim these same capital losses to defray 20 years of income taxes
4) Allowing him to re-leverage and live high off the hog again
5) Lather, rinse, repeat?
Think that's it?
Election Model Update
9/30 Update9/27 Update
9/25 Update
9/24 Update
9/21 Update
9/22 Update
9/1/2016 update
8/16/2016 update
Update with drift included 8/6/2016
Original Model Writeup 8/3/2016
Model projections:
#############################################
# INSTANTANEOUS MODEL
#############################################
Instantaneous Probability of a Clinton Win: 75.31 %
Mean Electoral Votes Clinton Currently Winning: 295.02
Median Electoral Votes Clinton Currently Winning: 298.0
Maximum Likelihood Electoral Vote Scenario for Clinto: 301
#############################################
# PROJECTING RESULTS TO NOVEMBER
#############################################
Probability of a Clinton Win if Current Trends Continue: 65.45 %
Mean Electoral Votes Clinton Projected to Win: 286.99
Median Electoral Votes Clinton Projected to Win: 288.0
Maximum Likelihood Projected Electoral Vote Scenario: 270
Predicted National Point Spread (Clinton = +, Trump = -) 1.98
Effectively unchanged since yesterday.
Election Model Update 9/30
9/27 Update9/25 Update
9/24 Update
9/21 Update
9/22 Update
9/1/2016 update
8/16/2016 update
Update with drift included 8/6/2016
Original Model Writeup 8/3/2016
Model projections:
#############################################
# INSTANTANEOUS MODEL
#############################################
Instantaneous Probability of a Clinton Win: 74.51 %
Mean Electoral Votes Clinton Currently Winning: 294.38
Median Electoral Votes Clinton Currently Winning: 297.0
Maximum Likelihood Electoral Vote Scenario for Clinto: 303
#############################################
# PROJECTING RESULTS TO NOVEMBER
#############################################
Probability of a Clinton Win if Current Trends Continue: 66.5 %
Mean Electoral Votes Clinton Projected to Win: 286.49
Median Electoral Votes Clinton Projected to Win: 288.0
Maximum Likelihood Projected Electoral Vote Scenario: 291
Predicted National Point Spread (Clinton = +, Trump = -) 1.93
Long range forecast starting to climb significantly again. Slight reduction in instantaneous forecast, likely just noise in the distribution estimates. Expect instantaneous forecast to converge to long range in the next few weeks.
Interesting to see what happens with Sam Wang's Princeton Election Consortium at the next update
UPI/CVoter (Moonies and some Brand-X Indian public opinion outfit) just dumped a bunch of shitpolls for all 50 states.
It will be interesting to see what this does to Wang's numbers as Pennsylvania is heavily leveraged (a swath of recent, suspect close or Trump leaning polls) in the last week or so.
The one thing I like about Wang is that his methodology resists outliers. But sometimes you get a sequence of bad polls. It happens. It knocked my model off a few points. I'm hopeful his is more resistant.
(on edit: no I don't think it's real. It's just an interesting opportunity to test a hypothesis).
How to do as well as 538 with only National Poll Averages (or why I'm jealous of Nate Silver).
So I was recently accused by a DUer (whom I hold in the highest esteem) of being jealous of Nate Silver. While this is undoubtedly true, I want to really dig into the roots of my jealousy. Trauma buried this deep needs to be excavated and examined, before one can really begin to heal.
You see, Ive been very disturbed by Silvers methodology this year, the way it gyrates almost in sync with the polls, when what it is SUPPOSED TO DO is aggregate the information in the polls and give us a stabler and truer picture of where the race is (and maybe where its headed).
My suspicion has been that all Nate has really constructed is a glorified poll average, with all his other bells and whistles providing marginal added value (if any at all).
So with that in mind, I converted two graphics, one from the Huffington Post pollster site (formerly pollster.com) and one from Silvers site and looked at the data from the last 117 days or so. The Huffpost data I rasterized the default smoothed national poll averages for HRC and DJT. From 538, the polls-only win probabilities.
I then constructed two non-linear models from the HuffPost data. Model 1 performs a multiple regression of Trumps 538 win probability (you only need his, because if you know his, you know hers, assuming no third parties can win) against the Trump national poll average from HuffPost, and the square of the poll average. Model 2 adds the Clinton poll average and the square of this poll average to the mix. The resulting plots can be seen below (note graph inverted due to direction convention on JPEG indices. If it bothers you, think of it as HRC's win prob).
As you can see, Model 1 (Polynomial Model Trump Poll Average in the legend) approximates the 538 curve reasonably well. Really very well. It captures 71% of the variability in the 538 Trump win probability. Model 2 1 (Polynomial Model Both Poll Average in the legend) is even better. It captures 87% of the variability in the 538 Trump win probability. The lower graph shows just how well this model tracks the 538 probabilities.
Plotting the output of the model against the 538 probabilities, you can see a strongly linear relationship.
There is a little structure to the noise, but its nothing to write home about, and I could probably reduce it further by adding a few more terms to the model. But capturing almost 90% of the variability, well, you are probably going to be right in ~90% of elections. Unless a razor thin year 2000 scenario comes up, you should be just fine looking at the national poll averages to see who will win.
So
why am I jealous of Nate Silver? Because hes got one hell of a scam going on right now.
I coulda been a contender.
LOL the Doofus Army has #TrumpWon trending on twitter
Yes, if I close my eyes, you're not there anymore...
(hums to self)
Image of the night
?w=800&h=273Election Model Update
9/25 Update9/24 Update
9/21 Update
9/22 Update
9/1/2016 update
8/16/2016 update
Update with drift included 8/6/2016
Original Model Writeup 8/3/2016
Model projections:
#############################################
# INSTANTANEOUS MODEL
#############################################
Instantaneous Probability of a Clinton Win: 76.73 %
Mean Electoral Votes Clinton Currently Winning: 297.65
Median Electoral Votes Clinton Currently Winning: 300.0
Maximum Likelihood Electoral Vote Scenario for Clinto: 296
#############################################
# PROJECTING RESULTS TO NOVEMBER
#############################################
Probability of a Clinton Win if Current Trends Continue: 62.97 %
Mean Electoral Votes Clinton Projected to Win: 284.22
Median Electoral Votes Clinton Projected to Win: 285.0
Maximum Likelihood Projected Electoral Vote Scenario: 280
Predicted National Point Spread (Clinton = +, Trump = -) 3.73
Analysis: New batch of Ipsos-Reuters polls bumped up the instantaneous forecast. Long range more or less the same (this is due to the variance of the states from which I'm sampling. Lean R states have been more consistent than lean D states. Still this long range number is better than what I ran (but did not post) yesterday.
Eventually both forecasts should converge.
Profile Information
Member since: Thu May 26, 2016, 09:07 AMNumber of posts: 4,602