Loki Liesmith
Loki Liesmith's JournalElectoral vote model update.
Two models: one that only uses current polling, and one that takes the current poll as a starting point and and includes a random drift term...essentially projecting the current scenario forward to the election.
Previous model writeups:
Update with drift included 8/6/2016
Original Model Writeup 8/3/2016
Model projections:
Probability of D win using current polling: 93.8%
average number of electoral votes: 326.4
median number of electoral votes: 330
most common electoral scenario: 337 electoral votes
Probability of D win projected forward to November election: 79.3%
average number of electoral votes: 299.3
median number of electoral votes: 301
most common electoral scenario: 293 electoral votes
model appears to be converging to consensus estimates.
Election Model Update
For the original model writeup, see here.
I made some tweaks to the model, and allowed for a random "drift" in the current numbers, based on the average variance per day (drift variance) in polling data from each individual state. This allows the model to calculate a "forward likelihood" of an outcome assuming the values drift from the current electoral estimate in a stochastic fashion. Drift variance in polling numbers are estimated for each state directly from polling data from the beginning of 2016. For states with no polling data, we average over all known state drift variances and use that value. So we will get two win outcomes: an outcome if the election was held today...and the probability of that same outcome happening in November.
With this in mind the model generates the following outcomes:
If the election were held today, the probability of a Democratic win is
87.3%
and the probability of an R win is
12.7%
with an average of 308 electoral votes, and a median of 310 for the Democrats. The most likely outcome for Dems is 322 EVs
####################################################
The probability of a D win in November is:
73.6%
and for the Rs:
26.4% (of course)
with an average of 289 electoral votes, and a median of 291 for the Democrats. The most likely outcome for Dems is 296 EVs.
Electoral Vote Model: Description and initial run. 80.6% probability of Dem Win.
So everyone and their brother has an election model these days I figured I should try and put one together too.
It's a fairly simple model and it samples polls via the Huffington Post Pollster API. I use a median filter moving average to estimate the likely spread between Democratic and Republican (D-R) percentages for each state for which polling is available.
There are many states for which no polling is available yet. Default D-R spreads for each unknown state are assigned using a heuristic: Deep South states have a strong (20 point) bias in favor of Republicans...Unpolled New England states have a 5 point bias toward Democrats. Each unpolled state has an implicit variance in this estimate derived from the average margin of error in polled states.
For states with polling, state variance is estimated from the average variance of the most recent polls from that state (usually between 3 and 5 polls). If there are no polls in the current monthly interval, we estimate a trend from older data and calculate the likely D-R spread based on this trendline.
Electoral votes are assigned to Democrats for positive D-R speads, Republicans for negative spreads.
The model is run 10000 times, with random noise added to each spreads based on the variances estimated above.
Today's model run predicts an 80.6% probability of a D win and 19.4% probability of an R win, with an average of 290 electoral votes for the Democrat and a median and mode of 292 electoral votes.
An histogram of outcomes for Democratic Electoral Votes - Republican Electoral Votes is shown below. Outcomes above zero are scenarios where Democrats win the electoral vote.
Profile Information
Member since: Thu May 26, 2016, 09:07 AMNumber of posts: 4,602
