Slate/Votecastr real time election projections

[Erich Maria Remarque]

I'm not sure what Arch's activities were on that thread, but I know that I invested nothing in those numbers. All they showed were early and absentee voting by party identification; that didn't prove anything to me in terms of votes for Clinton or Trump.

So you are saying, you weren't "projecting" NV, CO and VA in to Clinton's pocket based on EV. Or Florida?

This model does basically the same, but uses sophisticated algorithms. Obama used similar

[Erich Maria Remarque]

Haha, Dems were OK with CO projection, where Hillary did much better than Obama, but now it a trash because of Nevada

[Erich Maria Remarque]

One thing to remember about this model is that it is like the play-by-play for a sports game. It will move over the day based on when certain voters cast their votes. However if there are large leads that build up early, it will show just like a team that scores a lot early in the game.

But should Nevada's EV not be much more D-friendly?

[Erich Maria Remarque]

Haha, Dems were OK with CO projection, where Hillary did much better than Obama, but now it a trash because of Nevada

CO is not a projection, it is the modeled vote of individual people matched against the voter file who have already actually voted.

This is apparently different from other states where they do not have voter file individual level data on who has voted, but only know the total # of people who have voted in particular precincts (but not necessarily which individuals have voted in those precincts).

And including Stein in Nevada is of course obviously a dumb screw up.

And there is a difference in what early vote means in different states.

So basically there are large differences in what they are reporting for different states.

But those with large EV, as Nevada? Does they not use voter file for EV there?

As I undrstand they use voter file for all EV?

You must be logged in to read this quote.

So it is projection. By using voter file. Other only by their model of turnout and polls

[Erich Maria Remarque]

They are missing votes both there and in Florida.  

I know they are. But they are using voter file for EV in all states, right?

[Erich Maria Remarque]

So far they ONLY used EV data and they are using voter fill.

They are still processing Florida EV data and maybe other states as well. Nevada?

You must be logged in to read this quote.

[Erich Maria Remarque]

But they can only do this when they have individual level data on which particular people have voted (like they apparently do for CO, but not other states).

Are you sure, as I understand, they project early voting in other stated as well.

Projection of early voters. I didn't say anything about projection of who win the state. It is pretty meaningless.

But we can compare their projection of early voting with polls. Some polls ask voters who already voted. For instance if their projections is much Trump-friendly = polls probably underestimate him. And vice versa.

[Erich Maria Remarque]

Local officials collect and report information about who voted early in each state, and VoteCastr then compares that public info with its own private early voter files.

The key point that is somewhat glossed over is that the "information" that the "local officials" report can be different in different states. In some states, that information may be a list of the voter ID numbers of which specific individuals have already voted. For other states, that "information" may just be a report that 578 voters have voted early in precinct 42, without specifying which particular voters it is who have voted.

Eh. They clearly stated that they would use voter file. If it was only "report that 578 voters have voted early in precinct 42", they'd likely tell us about it.

[Erich Maria Remarque]

Other than an additional dump of early vote from FL, the numbers haven't updated since the site went live.  I guess they're still working through some issues running the data?

As I understand, they have right now only EV data. But Florida is so large, that it take time to process all the data. Someone could check, which states match final EV data and which doesn't. Apparently, FL and NV are still not processed fully.

[Erich Maria Remarque]

You didn't already realize that? Only Edison Research conducts those.

Yeah, not until now. I was deceived by their "this is controversial" and their "big networks hold this back" hype.

You should always start by reading the f**king instruction . Americans

[Erich Maria Remarque]

Not trying to belittle.
How is this different than any twitter account who gets early voting stats and analyzes them? Are they conducting polls? Do they have information the public doesn't have?

As I understand. They conducted a poll with huge sample size, so it could be well calibrated proportionally to voter file. Geographically, party registration, age, etc, those who voted in 2012/2014, those who didn't etc. They probably use even more sophisticated voter modelling.

Then they use those voters as LV screen. If 4% of 20-25 years old white female Trumpistas from Las Vegas voted early and 15% on ED. They extrapolate this data on all voters voted so far in EV and ED respectively.

So yeah, it is just a really big poll, similar to those from Upshot/Sienna.

[Erich Maria Remarque]

Nate Cohn article on this: http://www.nytimes.com/2016/11/08/upshot/you-may-need-a-strong-stomach-for-the-pitfalls-of-real-time-election-projections.html?_r=0

"Don't throw up because of the Slate/Votecastr live projections"

Live during the day, yeah. But now they are estimating EV. You know, the stuff that you all did in    "absentee/early vote thread"

The only difference, is that they have data-science education. So their model is likely better

[Erich Maria Remarque]

But they can only do this when they have individual level data on which particular people have voted (like they apparently do for CO, but not other states).

Are you sure, as I understand, they project early voting in other stated as well.

Projection of early voters. I didn't say anything about projection of who win the state. It is pretty meaningless.

But we can compare their projection of early voting with polls. Some polls ask voters who already voted. For instance if their projections is much Trump-friendly = polls probably underestimate him. And vice versa.

Sorry, what I mean (but forgot to explicitly say) is that once they have the modeled support score for each registered voter in the voter file, they will have data such as Amanda X has a .7 Clinton support score. That means they estimate that there is a 70% probability that Amanda X supports Trump. And they have data that Joe Y has a .4 Clinton support score.

So then if they have individual data for who has voted, they can then just add up each individual's support score and average it by the total number of people who have voted. So for example, if the only 2 people who have voted in a precinct are Amanda X and Joe Y, then the estimated vote is (.7 + .4) / 2 = .55. So they estimate Clinton has 55% support there (out of 2 votes cast, 1.1 votes for Clinton, .9 votes for Trump).

But you can only do this if you know specifically which individuals have voted - if you know that Amanda X and Joe Y are the particular people who have voted.

If you don't know that, but instead just know that 5 people have voted in Precinct Z and 3 people have voted in Precinct Q, then what you do for both of those precincts is to take the support scores of all the registered voters in each of those precincts weighted by their turnout scores, and that gives you your estimated vote percentage in that precinct. Then you can get your statewide or countywide vote estimate by averaging those weighted by the known aggregate turnout in each precinct. For example, if the average turnout-score weighted support-score in precinct Z is .7 Trump and for precinct Q is .2 Trump, then the estimated vote would be .7 * 5 + .2 * 3 = 4.1 votes estimated for Trump. Since there are a total of 8 votes, that then means 3.9 estimated votes for Clinton (not counting 3rd parties for this example).

So that is what they do for states that have early vote, but in which the state does not report to them which particular individuals have early voted.

I wasn't even arguing that much about the methodology I assume that it is pretty good.

So if it is, we can compare their estimation of EV to the poll's estimation of EV. For instance, the polls showed that Hillary is winning EV by 6-10% in Florida and by 10% in NV (according to PPP). If we see that their estimation is ~similar, we know that polls were about right. If their estimation of EV is outside those bounces, we may conclude that polls overestimate one or another candidate. Or at least, that we have some indications. I know that this model also is based on polls, so it can also underestimate Hispanics or whatever group it might be. But still it is interesting to compare.

That's my point.

[Erich Maria Remarque]

Should we be worried about those PA numbers?

It's just based on by mail absentee, so its a very small number, and should be GOP leaning.

Nevada?

[Erich Maria Remarque]

Should we be worried about those PA numbers?

It's just based on by mail absentee, so its a very small number, and should be GOP leaning.

Nevada?

Pennsylvania only has excuse absentee balloting and no early voting, giving the GOP a decisive edge among the relatively few absentee ballots due to mostly older, whiter voters casting them. Almost all vote in Pennsylvania comes in on election day.

But I asked about Nevada

Though, they have only 580k of 770k that voted. I assume that last few days were very good to D, at least according to NV guru.

[Erich Maria Remarque]

They will have new numbers in about half an hour

So much hype for "real-time" data...

I mean, Nevada has in person early voting so is not comparable at all to Pennsylvania. Dems have built a similar lead to 2012 there, especially in Clark County, and the unaffiliated voters are younger and more diverse than 2012 due to Democratic registration efforts over the last 2 years.

I'm asking if Trumpistas should be sad based on results from this model

[Erich Maria Remarque]

I'm asking if Trumpistas should be sad based on results from this model

Your question seems to imply that Trumpistas have feelings?

Only:

SAAAAD!

ARRGH!

[Erich Maria Remarque]

Updated data. Looks great for Clinton. Lead everywhere.

Especially Florida, where her lead has increased to over 200k votes.

Why is it good? It is EV data.

According to polls
a) Clinton has about 6-10% lead in Florida, 10% in Nevada in 26%(!!!) in WI (according to PPP). According to this just 3%
b) Trump will be doing much better.

It this model is right, than polls overestimated Trump heavily...
Both in FL and NV and WI

But I doubt.

https://twitter.com/ppppolls/status/795455957765681152

You must be logged in to read this quote.

https://twitter.com/PpollingNumbers/status/794571735760797697

You must be logged in to read this quote.

So either the model is bad, PPP are junk/partisan or Trump is your next president

[Erich Maria Remarque]

There was a new data dump, vote totals in Florida are now about 7.3 million. A lot of that is early vote, but the morning wave was dumped in as well... so the EV margin is holding.

Put it another way, if Clinton adds another 400k votes, and Trump adds another 500k votes, they hit the Obama/Romney margin. They are very close to 2012 totals already.

I am talking about this vs polls. Purely.
But you're right. They now have 1mln ED voters for Florida and 0.7mln for Wisconsin. But NV and NH seems to look pretty good for Trump so far.

[Erich Maria Remarque]

The third party support seems overinflated. Who the  votes early for a protest vote?

Actually, Johson is pretty much as 538, maybe overperforming by 1% point.

[Erich Maria Remarque]

These numbers are beyond inefficient to hold off the working class/after work Trump vote. Looks like 2000 all over again at the very best.

IDK, pretty good for Hillary.

But do we know that Trump's supporters vote late?

If there weren't for Florida numbers, I could think this should be nice for Trump with NV,OH and IA numbers. But, with FL it's a ball game.

Yep. Exactly my thoughts. Hispanics will win Florida for Hillary

[Erich Maria Remarque]

We are all aware that these are just made up numbers right?

As Dems in "early voting thread"

[Erich Maria Remarque]

If Trump is losing Florida by 4%, he needs to win the rest by 12% margin

[Erich Maria Remarque]

Could we all please calm down and not attack each other about this?  Let's face it, this is a new and unproven technique.  It's interesting to follow, but we will have no idea how accurate or useful it actually was until the full election results are available.

Only those who don't like/buy it are attacking. If you don't like, stop commenting it and calling it junk.

One post is enough.

[Erich Maria Remarque]

They don't even really have EV. They "estimate" it

SAD!

You must be logged in to read this quote.