Nov

03

2012

Justin Taylor|10:18 am CT

Which Presidential Polls Were Most Accurate in 2008? (Updated)

Update: See the correction below from a commenter:

That “Initial Report” list is outdated and invalid. It was compiled in the hours immediately following the election, long before all votes had been counted. It was based on an estimate of a 6.15 percent Obama lead. However, Obama actually won by a 7.2 margin, 52.9 to 45.7 percent (FEC verified).

Fordham later released a complete analysis based on the official popular vote outcome. In this report, Pew and Rasmussen scored much lower, being beat out by eight other pollsters.

[Original post below.]

According to Fordham University political scientist Costas Panagopoulos, the most accurate pollsters in the 2008 presidential election were the Pew Research Center and Rasmussen Reports. Pollsters, on average, tended to overestimate Obama’s support, though not by much. 17 of the 23 pollsters overstated Obama’s final count; 4 of the 23 underestimated it; 2 of the 23 (Pew and Rasmussen) got it exactly right.

Here’s the ranking:

1T. Rasmussen (11/1-3)**

1T. Pew (10/29-11/1)**

3. YouGov/Polimetrix (10/18-11/1)

4. Harris Interactive (10/20-27)

5. GWU (Lake/Tarrance) (11/2-3)*

6T. Diageo/Hotline (10/31-11/2)*

6T. ARG (10/25-27)*

8T. CNN (10/30-11/1)

8T. Ipsos/McClatchy (10/30-11/1)

10. DailyKos.com (D)/Research 2000 (11/1-3)

11. AP/Yahoo/KN (10/17-27)

12. Democracy Corps (D) (10/30-11/2)

13. FOX (11/1-2)

14. Economist/YouGov (10/25-27)

15. IBD/TIPP (11/1-3)

16. NBC/WSJ (11/1-2)

17. ABC/Post (10/30-11/2)

18. Marist College (11/3)

19. CBS (10/31-11/2)

20. Gallup (10/31-11/2)

21. Reuters/ C-SPAN/ Zogby (10/31-11/3)

22. CBS/Times (10/25-29)

23. Newsweek (10/22-23)

HT: The List

9 Comments

  1. That “Initial Report” list is outdated and invalid. It was compiled in the hours immediately following the election, long before all votes had been counted. It was based on an estimate of a 6.15 percent Obama lead. However, Obama actually won by a 7.2 margin, 52.9 to 45.7 percent (FEC verified).

    Fordham later released a complete analysis based on the official popular vote outcome. In this report, Pew and Rasmussen scored much lower, being beat out by eight other pollsters.

    http://www.fordham.edu/images/academics/graduate_schools/gsas/elections_and_campaign_/2008%20poll%20accuracy%20panagopoulos.pdf

  2. It might be more helpful to know which presidential polls have been most accurate across numerous election cycles rather than in a single election.

  3. Also, it would be more helpful to know which polls best predict the electoral college results. That is, after all, how our president is elected — NOT by popular vote.

    • The popular vote is actually a very good prediction of electoral college results. It is extremely rare for the winner of the popular vote to lose the electoral college. However, because it happened recently, people tend to think it’s a lot more likely than it actually is.

      When it does happen, it’s more likely to happen when a census hasn’t taken place in a while and some states are represented disproportionate to their population. However, the most recent census was just two years ago and electoral changes were made last year, so there shouldn’t be any states wielding disproportionately greater/lesser electoral vote influence relative to the size of their population.

      • Good point. I guess I was thinking more in lines of how close the election would be. When I see a 5-7% margin in the popular vote, I think it’s close — but then the electoral college results may show a blow out.

  4. I sometimes lie on polls because I do not believe it is any of their business. I try to keep it even though just to be fair. :>P

  5. http://theconservativetreehouse.com/2012/11/04/polls-schmolls-but-bickers-and-berry-appear-incredibly-accurate-romney-in-an-electoral-landslide/

    These guys (Bickers and Berry) have been right on every presidential elections since 1980!

    They are not a poll but an analysis based on individual state economic conditions (real per capita income, unemployment, changes in personal income, etc.)

    As of yesterday, they predict Electoral Vote as follows:
    • Romney: 330 (up from 315-320 a month ago)
    • Obama: 208

  6. Before Christians do too much navel-gazing, they should factor in that Romney’s get-out-the-vote effort turns out to have been a huge technological failure.

Comments are closed.