I am writing this column the afternoon before the election, but one thing I feel comfortable predicting: Several famous pollsters will be wrong.
For instance, in Minnesota either Zogby (Mondale by six) or Mason-Dixon (Coleman by six) will be left to explain how the dastardly public undercut them at the last moment. Likewise in Colorado, either Zogby (Strickland by five) or Gallup (Allard by two) will grumble about the public not truly understanding the full range of possibilities inherent within the phrase "a 95 percent chance of accuracy within a margin of error of plus or minus 4.5 percent." Properly understood, of course, that phrase means it could be a landslide either way.
Zogpiss has Special Sauce all over his face tonight.
Maybe the writer has been reading FR where we have been saying Republicans don't answer unavailable! LOL!!!
Agree with everything he says and I sincerely hope the Zogby is king people on here see what happened tonight! And also with Dick Morris!
Amen, my friend. Zogby is a bigger loser tonight
Couldn't happen to a nicer bunch of people if you ask me -- the clinitons, daschle, mcauliffe, zogby. Pretty good night for our side!
*** This problem has been building ever since cheap answering machines became available about 10 years ago. But with the mass use of cheap cellphones the problem is crossing over into a crisis for practitioners of the polling arts.****
This has been obvious to every polling company, and every news outlet that tried to keep it a secret. They used polls to shape campaigns. Now maybe with the fading of even organizations like VNS we will have more reporting of facts, and candidates words rather than the agencies favorite poll numbers.
http://www.zogby.com/news/ReadNews.dbm?ID=648
Zogby's take on 2002
Released: November 07, 2002
Wow!
Its been 36 hours after the results first began to trickle in, and thats still my reaction to the plethora of surprises which defined the 2002 Midterm Elections.
As a fan of politics nothing could be more exciting than seeing the unexpected occur again and again.
But as a political pollster, whose reputation is impacted seemingly by every race polled and every percentage point reflected, Election Night was cause for much more grimacing than we at Zogby International have been used to over the last several years.
Our record for accuracy has been well-documented and well-earned.
§ In the 2000 Presidential elections, we were the only polling firm in the nation to have Al Gore ahead in the popular vote. He won by 1 percent.
§ Zogby International came the closest in predicting the outcome in the Super Tuesday 2000 election.
§ In 1996, Zogby International was the only pollster nationwide to accurately call the 1996 Presidential race within 1 percent of the actual result.
As a result, it is no longer disputable that Zogby International has done consistently better in tighter races, than all of those who have just done well.
And for the 2002 Midterm Elections, we did have our usual on-target projections that most other polling firms missed Florida, North Carolina, Arkansas, New Jersey and Missouri.
But on the other hand, we had some which for us were absolute stunners -
Colorado, Illinois, and Georgia.
It makes me wonder, what went wrong?
Youve heard of the cliché: This is not rocket science. Guess what?! In an ever increasing magnitude, polling - or the science of opinion research - is becoming rocket science.
Fact is, this stuff aint easy!
In a world where hang-ups, cell phones and increasingly lower response rates add to the difficulty of accurately measuring just what Americans really think, the fact that all of us in the polling industry do as well as we do is really a tribute.
Ive just received preliminary results of the first five states in our post-election surveys. The results are right on the money with the actual election results. This tells me that there is no problem with our sampling, our interviewing, or perhaps any of the other possible problems associated with pre-election polling. It just means that there are more and more variables, and that we in the polling industry must continue to adapt in making sure opinion research keeps up with an increasingly knowledgeable and increasingly changing public.
I think one of the voter variables we are going to have to take a closer look at is late voter decision. In 1998, there were 10 states we deemed too close to call. When post-election polling was conducted, we discovered that 8 percent of those who voted said they made up their mind on election day!
That is very significant and something along with several other variables we at Zogby International plan to reassess for all our upcoming political polling.
Its my opinion that the New York Yankees are the best team in baseball. The record of achievement speaks for itself.
Yet, as we all know, the Yankees did not win the World Series this year.
And just like the Yankees, we at Zogby International strive to offer the most accurate opinion research available throughout the entire polling industry.
This year, we were just
okay.
Which for us, is not good enough.
(sorry the following numbers are ugly...maybe someone else can clean it up for me)
Arkansas - MSNBC/Arkansas Gazette/Zogby Poll - Governor
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Mike Huckabee (Republican)
49
50
51
54
53
Jimmie Lou Fisher (Democrat)
37
40
40
44
47
Arkansas - MSNBC/Arkansas Gazette/Zogby Poll - Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Tim Hutchinson (Republican)
43
45
44
43
46
Mark Pryor (Democrat)
45
45
55
56
54
Colorado MSNBC/Zogby Poll - Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Wayne Allard (Republican)
42
40
44
46
51
Tom Strickland (Democrat)
42
41
53
51
45
Rick Stanley (Libertarian)
-
5
3
2
1
Georgia MSNBC/Zogby Poll Senate
Nov. 2
Final Results
Actual Results
Max Cleland (Democrat)
49
50
46
Saxby Chambliss(Republican)
49
48
53
Sandy Thomas (Libertarian)
2
1
1
Minnesota MSNBC/Zogby Poll - Governor
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Tim Pawlenty (Republican)
28
30
35
39
45
Roger Moe (Democrat)
23
25
34
38
36
Tim Penny (Independence)
28
27
18
18
16
Ken Pentel (Green)
2
3
3
5
2
Minnesota MSNBC/Zogby Poll - Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
W. Mondale (Democrat)
(Wellstone) 41
(Wellstone) 46
50
51
48
N. Coleman (Republican)
47
37
45
45
50
J. Moore (Independence)
2
6
3
2
2
R. Tricomo (Green)
1
1
-
2
-
Missouri MSNBC/St. Louis Post-Dispatch/Zogby Poll Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Jean Carnahan (Democrat)
48
41
49
45
49
Jim Talent (Republican)
40
47
48
53
50
Daniel Digger Romano (Green)
0
0
1
1
1
Tamara Millay (Libertarian)
1
1
1
1
-
New Jersey MSNBC/Zogby Poll - Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Frank Lautenberg (Democrat)
39
48
54
55
54
Douglas Forrester (Republican)
34
36
38
42
44
John Ted Glick (Green)
3
1
5
2
1
Liz Macron (Libertarian)
2
1
1
1
1
*Torricelli withdrew from the campaign.
North Carolina MSNBC/Zogby Poll - Senate
Sept. 21
Nov. 2
Final Results
Actual Results
Elizabeth Dole (Republican)
55
52
53
54
Erskine Bowles (Democrat)
32
46
43
45
Sean Haugh (Libertarian)
1
3
4
1
Not sure
11
-
-
South Dakota MSNBC/Zogby Poll - Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Tim Johnson (Democrat)
46
43
52
47
50
John Thune (Republican)
43
45
47
52
49
Kurt Evans (Libertarian)
2
3
1
1
1
Not Sure
10
10
-
Texas MSNBC/Zogby Poll Governor
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
Rick Perry (Republican)
44
52
50
58
58
Tony Sanchez (Democrat)
32
30
36
38
40
Rahul Mahajan (Green)
1
1
1
1
1
Jeff Daiell (Libertarian)
4
2
1
2
1
Texas MSNBC/Zogby Poll Senate
Sept. 21
Oct. 12
Nov. 2
Final Results
Actual Results
John Cornyn (Republican)
42
45
49
50
55
Ron Kirk (Democrat)
30
37
48
46
43
Roy Williams (Green)
1
3
1
1
1
Scott Jameson (Libertarian)
3
2
2
2
1
Wright
1
5
1
1
-