Skip to main content

For the poll obsessed here, understanding how different odds makers are coming up with their projections can be difficult.  My own model is pretty complicated, and I run about 20,000 election simulations to create it.

But the basic idea is pretty simple: you calculate the odds of winning a state based on the polling, and then you run a bunch of simulations to see what the probably result is.  Now there are some flaws in this more basic approach (eg dependent versus independent variables) but the basic principle is simple.

So I created a more simplified model that you can use.  If you follow the link below, you can enter your odds for each state, and generate the probability of an Obama victory.  Because of limitations with Google docs, this runs only 1,650 or so simulations, but the basic idea is pretty straightforward (and it took only an hour to create).

https://docs.google.com/...

If you find an bugs send me a message here or at on twitter at dcg1114.

Before anyone asks - I am part of the legal protection team here and will be working over the next week.

EMAIL TO A FRIEND X
Your Email has been sent.
You must add at least one tag to this diary before publishing it.

Add keywords that describe this diary. Separate multiple keywords with commas.
Tagging tips - Search For Tags - Browse For Tags

?

More Tagging tips:

A tag is a way to search for this diary. If someone is searching for "Barack Obama," is this a diary they'd be trying to find?

Use a person's full name, without any title. Senator Obama may become President Obama, and Michelle Obama might run for office.

If your diary covers an election or elected official, use election tags, which are generally the state abbreviation followed by the office. CA-01 is the first district House seat. CA-Sen covers both senate races. NY-GOV covers the New York governor's race.

Tags do not compound: that is, "education reform" is a completely different tag from "education". A tag like "reform" alone is probably not meaningful.

Consider if one or more of these tags fits your diary: Civil Rights, Community, Congress, Culture, Economy, Education, Elections, Energy, Environment, Health Care, International, Labor, Law, Media, Meta, National Security, Science, Transportation, or White House. If your diary is specific to a state, consider adding the state (California, Texas, etc). Keep in mind, though, that there are many wonderful and important diaries that don't fit in any of these tags. Don't worry if yours doesn't.

You can add a private note to this diary when hotlisting it:
Are you sure you want to remove this diary from your hotlist?
Are you sure you want to remove your recommendation? You can only recommend a diary once, so you will not be able to re-recommend it afterwards.
Rescue this diary, and add a note:
Are you sure you want to remove this diary from Rescue?
Choose where to republish this diary. The diary will be added to the queue for that group. Publish it from the queue to make it appear.

You must be a member of a group to use this feature.

Add a quick update to your diary without changing the diary itself:
Are you sure you want to remove this diary?
(The diary will be removed from the site and returned to your drafts for further editing.)
(The diary will be removed.)
Are you sure you want to save these changes to the published diary?

Comment Preferences

  •  Tip Jar (2+ / 0-)
    Recommended by:
    terjeanderson, Jahiegel

    The bitter truth of deep inequality has been disguised by an era of cheap imported goods and the anyone-can-make-it celebrity myth - Polly Toynbee

    by fladem on Mon Oct 29, 2012 at 10:28:47 AM PDT

  •  This is awesome (1+ / 0-)
    Recommended by:
    fladem

    Is there anyway to make the histogram chart in Google Docs?

    GOP: The Party of Acid rain, Abortion of the American Dream, and Amnesty for Wall Street.

    by Attorney at Arms on Mon Oct 29, 2012 at 10:47:52 AM PDT

  •  My simulation gave Obama a 94% chance of winning (2+ / 0-)
    Recommended by:
    fladem, terjeanderson

    I think I'll take that.

    (-8.38, -4.72), CT-02 (home), new ME-01 (college) "The needs of the many outweigh the needs of the few, or the one." -Spock

    by ProudNewEnglander on Mon Oct 29, 2012 at 10:58:07 AM PDT

  •  Unfortunately, (0+ / 0-)

    the probability of an EC win in this speadsheet assumes that the less probable outcome in each state is independent from that probability in others, when, in fact, the ~1% probability of a Romney win in Washington would be highly correlated with more probable Romney wins in Oregon, Virginia, Pennsylvania, Minnesota, and Wisconsin; and likewise an Obama win in Indiana and Missouri would be highly correlated with winning North Carolina, Florida, Arizona, and all the current Obama leaning states.

    This model treats highly-dependent variables independently, meaning that this spreadsheet grossly overestimates the certainty of a given outcome. Maybe you could run each of your scenarios with a "master" random number accounting for about 80% of the probability in all of the states, with an independent probability for each to account for the remaining 20%.

    •  Hope you see this (0+ / 0-)

      so you are right: it does treat each as an independent event.  Here is why:
      1.  this assumes any systematic shift would be captured since it is assuming the election will be held today
      2.  There is no real way to model the odds of a systemic shift because elections are to infrequent. In this I think Nate is actually dead wrong.

      You are right: this model captures polling error, not the risk that a wave might develop that moves all of the races in one direction.

      The bitter truth of deep inequality has been disguised by an era of cheap imported goods and the anyone-can-make-it celebrity myth - Polly Toynbee

      by fladem on Thu Nov 01, 2012 at 12:41:47 PM PDT

      [ Parent ]

      •  It's not really a wave that I would account for, (0+ / 0-)

        it's that undecideds and less-likely voters, whose tendencies pretty much define the probability curve in swing states, tend to move toward one of the candidates more than the other, meaning that the whole of the polling systematically underestimates the chances of the candidate who gets the bulk of the last-minute deciders. It's those undecideds and the effectiveness of GOTV efforts that need to be accounted for, and I don't think those are even remotely independent from state-to-state.

        •  And elections are too infrequent (0+ / 0-)

          to predict ahead of time which direction they will sing.

          You can, however, take the current average and move each by a point, and then compute the odds.  This would allow you to look at the effect against the baseline.

          The bitter truth of deep inequality has been disguised by an era of cheap imported goods and the anyone-can-make-it celebrity myth - Polly Toynbee

          by fladem on Thu Nov 01, 2012 at 09:17:37 PM PDT

          [ Parent ]

Subscribe or Donate to support Daily Kos.

Click here for the mobile view of the site