2008 Projections

President
Senate
Governors
House


Favorite Links

Viking Pundit
Wizbang!
Captain's Quarters
RealClearPolitics
Hugh Hewitt
PoliPundit
Michael Yon
PollingReport
Betsy's Page
The Hill Blog
Crystal Ball
Atlas of US Elections
OnTheIssues.org

Blogroll

The Adventures of Chester
The Anchoress
Backcountry Conservative
Baldilocks
Behind the Ballot
The Bleat
Blogs For Bush
Broken Masterpieces
The Bullwinkle Blog
By Dawn's Early Light
Byrd Droppings
California Yankee
A Certain Slant of Light
Citizen Frank
Citizen Smash
Command Post
Confederate Yankee
Conservative Grapevine
The Counterterrorism Blog
Crosstabs
The Cultural Report
Daily Pundit
Daly Thoughts
DANEgerous
Daniel Drezner
Dean's World
Ed Fitzgerald's unfutz
eTalkingHead
Evangelical Outpost
The Fourth Rail
Frank Williams
Freedom's Lighthouse
The Futurist
GOP Bloggers
GOP Video
Hang Right Politics
HobbsOnline
InstaPundit
Intellectual Conservative
Irish Pennants
Iowa Voice
Jeff Doolittle
JunkYardBlog
La Shawn Barber
Left Coast Conservative
letters from babylon
Libertarian Leanings
Little Green Footballs
Mark A. Kilmer
Mark Steyn
Matt Margolis
Michael Totten
Michelle Malkin
Murdoc Online
my election analysis
Mystery Pollster
NC Republicans
Near East Pundit
New England Republican
Ogre's Politics and Views
One Hand Clapping
Outside the Beltway
Pardon My English
Patrick Ruffini
Peat Bog
Pejmanesque
PoliBlog
The Politburo Diktat
PoliticalWire
Political State Report
Political Yard
Powerline
Quentin Langley
RedState.org
Right-Thinking
Right Wing News
Scrappleface
Sister Toldjah
Slublog
SoCalPundit
Stolen Thunder
The Strata-Sphere
Thoughts Online
Tim Blair
The Volokh Conspiracy
WILLisms.com
Winds of Change
The Word Unheard


 
 
Presidential Projection Formula
 
General Attributes of the Formula

I.  Purpose
This formula's intent is to give a general sense of how the presidential elections would turn out if the elections were held today.  As we move closer to election day, its usefulness as a prediction tool will increase.

II.  Objectivity
In developing the formula, I made every effort to be objective, rather than biased toward the GOP. Yes, I am Republican, but this formula does not, in any way, falsely inflate the GOP's standing.

III.  Polls
I try to be thorough and objective in gathering polling data.  I mostly use the Polling Report and RealClearPolitics for national polls and DC Political Report and RealClearPolitics for state polls.  However, there may be times when I overlook a poll.  If this happens, I urge my readers to alert me to such polls so that I can include them in the projections.

 
The Formula's Components

I.  Adjusted National Polling Data
Up to ten national polls are used to compute an average national margin between John McCain and Barack Obama.  Only polls two weeks old or less will be used.  The average national margin is then subtracted from the national 2004 result to arrive at the national polling data adjustment.  This adjustment is then added to the 2004 margin in each state, yielding the national polling factor for the state.

II.  State Polling Data
The aggregate average of polling data is used in the following manner:

  • At most, seven polls from a state are used.
  • In the interest of currency, if there is a poll or polls that were conducted less than 15 days prior to the update, then only such polls will be used.  For example, if a poll was conducted in Ohio a week before the update, and another was conducted three weeks before, only the newest poll will be used.
  • However, if the latest polls were conducted more than 15 days prior, they will be used.
  • In no case will a poll over 30 days old be used.
    Update (September 1, 2008):  If no polls have been released within the previous 30 days, older polls will be used.  Most likely, this will only apply in states where the outcome is not in doubt.  So, the validity of the projection should not be impacted by using older polls in these cases.

III.  Combining state and national polling factors
The state and national polling factors are combined to produce the state's Election Projection.  For the purposes of this calculation, the national polling factor is viewed as simply another state poll worth 1/2 a state poll (update October 20, 2008).  Therefore, if only one state poll is used, the national polling factor contributes 33% of the formula weight.  If two state polls are used, the national factor is reduced to 20%.  Three state polls reduce it to 14% and so on.  The idea here is that the more state polls have been released, the more accurate they should be and the less weight need be placed on a national polling component.

 
The Formula in action, an example

The formula:

  ((State Polling * No. state polls) + Nat. Polling) / (No. state polls + 1)

Here is an example of the calculations using the formula for Ohio (2008 numbers are from June 1):

  • 2004 National Result:  Bush +2.46%
  • 2008 National Polling:  Obama +3.64%
  • National Polling Adjustment:  Obama +6.10%
  • 2004 Ohio Result:  Bush +2.10%
  • 2008 Ohio Polling (3 polls):  Obama +1.33%
  • Weight:  State polls = 86%, National polls = 14%
  • Projected 2008 National Result: Obama 51.04%, McCain 46.96%
       NOTE:  Two percent is allocated to any third-party candidates.
  • Projected 2008 Ohio Result: Obama wins by 2.01%

posted by Scott Elliott at 12:10pm 06/07/08 ::


 
 
Senate and Gubernatorial Projection Formula
 
Components of the Formula

I.  Head-to-head Polling
The aggregate average of polling data is used in the following manner:

  • At most, seven polls from a state are used.
  • In the interest of currency, if there is a poll or polls that were conducted less than 15 days prior to the update, then only such polls will be used.  For example, if a poll was conducted in Ohio a week before the update, and another was conducted three weeks before, only the newest poll will be used.
  • However, if the latest polls were conducted more than 15 days prior, they will be used.
  • In the event that no poll has been released in the prior 30 days, a poll over 30 days old can be used.
The weight of this factor will be 85% if the incumbent is seeking re-election and 95% if not.

II.  Incumbent Job Approval
The last job approval numbers provided by Survey USA will used for this component.  Obviously, this factor is more relevant when the incumbent is seeking re-election.  So, the weight of this factor will be 15% if the incumbent is seeking re-election and 5% if not.

 
The Formula in action, an example

The formula for incumbents:

  (Head-to-head Polling * 85%) + (Job Approval * 15%)

The formula for open seat races:

  (Head-to-head Polling * 95%) + (Job Approval * 5%)

Here is an example of the calculations using the formula for the Indiana gubernatorial race (numbers are from June 1):

  • Head-to-head Polling:  Mitch Daniels (R) +7.4%
  • Job Approval:  Daniels -3%
  • Projected Result: Daniels defeats Thompson by 5.8%

Update (September 1, 2008):  Because approval numbers have proven to be hard to find and inconsistently measured, I have decided to remove the second component from the formula for my Senate and gubernatorial projections.

posted by Scott Elliott at 12:10pm 06/07/08 ::
 
Contested House Races Projection Formula
 
General Description

The formula for contested House races is substantially unlike the formulas I described above.  There are four main differences between this formula and the one used for Senate and gubernatorial races.  First, since job approval numbers for House members are extremely difficult to track, there is not a job approval component to the formula.

Second, published polls for district races are also much more difficult to find than for Senate or gubernatorial races, so I needed another metric which would be reliable and consistent throughout the election season.  The aggregate race ratings of four well-known pundits is that metric.  The predictions of Stuart Rothenberg, Charlie Cook, Larry Sabato, and the Congressional Quarterly will be used.  Since their predictions are qualitative (i.e. leans, toss-up, solid, etc), I will assign a margin of victory to them as follows:

Toss-up/
No Clear Favorite
Tilt Lean Likely/
Favored
Solid/
Safe
0% 2% 4% 8% 16%

Third, when polling data can be obtained, their weight be will based on whether one poll or multiple polls are available.  If one poll is available, it will get a 25% chunk of the projection.  If two polls have been published, the average will be taken, and that result will be 50% of the projection.  Currency stipulations posted in the Senate and gubernatorial formula explanation will apply here as well.

Finally, partisan polls will be used with a caveat.  The results will be adjusted by subtracting 3 points from the party of the pollster and adding them to the other party.  For example, if a Republican polling firm publishes a poll with the GOP candidate winning 54% to 40%, the poll will be entered into the calculations as 51% to 43%.

 
The Formula in action, an example

For races with no published polls:

Pundit Avg. * 100%
   NOTE:  Because I refuse to post a "toss-up" rating on any race, I will decide one way or the other in the event that pundit predictions result in a tie.  The margin for such races will be +0.5% for my best guess.

For races with one published polls:

(Pundit Avg. * 0.75) + (Poll * 0.25)

For races with two published polls:

(Pundit Avg. * 0.50) + (Poll * 0.50)

Here is an example of the calculations using the formula for the California District 11 race (numbers are from June 1, positive numbers favor incumbent party):

  • Pundit Predictions:  Factor = 2.0 for incumbent McNerney
    • Stuart Rothenberg:  Toss-up
    • Charlie Cook:  Toss-up
    • Larry Sabato:  McNerney by 4% (leans DEM)
    • Congressional Quarterly:  McNerney by 4% (leans DEM)
  • Polls:  Factor = 4.0 for challenger Andal
    • Benneson Strategy (D):  McNerney(D) 42%, Andal(R) 40%
  • Projected Result:  (2.0 * 0.75) + (-4.0 * 0.25) = 0.5%
    • McNerney defeats Andal by 0.5%
posted by Scott Elliott at 12:10pm 06/07/08 ::
 
2006 Election     2004 Election

Electoral Vote Projection

Click for details
Senate Projection

Click for details
House Projection

Click for details
Governors Projection

Click for details
Special Thanks To:

Charlie Cook
Cook Political


Congressional Quarterly
CQ Politics


D.C. Finegold Sachs
DC's Political Report


Dave Leip
U.S. Election Atlas


Larry Sabato
Crystal Ball


Tom Bevan and John McIntyre
RealClearPolitics

Election Projection Resources
 
EP's RSS Feed

RSS Feed  RSS
Search this site

provided by Google
Contact Me

e-mail Scott at:
electionprojection-at-
gmail <put a period here> com
State-by-State

Alabama
Alaska
Arizona
Arkansas
California
Colorado
Connecticut
Delaware
Florida
Georgia
Hawaii
Idaho
Illinois
Indiana
Iowa
Kansas
Kentucky
Louisiana
Maine
Maryland
Massachusetts
Michigan
Minnesota
Mississippi
Missouri

Montana
Nebraska
Nevada
New Hampshire
New Jersey
New Mexico
New York
North Carolina
North Dakota
Ohio
Oklahoma
Oregon
Pennsylvania
Rhode Island
South Carolina
South Dakota
Tennessee
Texas
Utah
Vermont
Virginia
Washington
West Virginia
Wisconsin
Wyoming
 

©Copyright 2008 Scott Elliott, All Rights Reserved

Top Politics blogs     Politics Blogs - Blog Top Sites