Regarding
the Research 2000 Pile-on
Markos Moulitsas of Daily Kos and Nate Silver of fivethirtyeight.com have each taken aim at Research 2000, which did the pre-election polling for Daily Kos.
Markos cites the Research 2000 poll that determined only 27% of Republicans supported gays in the military. He found this to be way too low. His evidence? Gallup and ABC polls had over 60% GOP support. Well, because they are MSM, that makes them right and R2000 wrong?
Markos gives Republicans too much credit. If 90% of Democrats support gays in the military as do 30% of Republicans and 60% of independents, then we would have about 61% supporting in total. In any case, why does Markos go after R2000, which did the 2008 pre-election presidential polling for him?
|
Party-ID |
Mix |
Support |
Total |
|
Dem |
40.0% |
90.0% |
36.0% |
|
Rep |
35.0% |
30.0% |
10.5% |
|
Ind |
25.0% |
60.0% |
15.0% |
|
Total |
100.0% |
- |
61.5% |
Nate Silver wrote that the R2000 data “feels way too clean for me”. Better clean than dirty, Nate. Would he rather see the kind of volatility that CNN and Gallup had in their tracking polls? For some reason, Wolf Blitzer always appeared perplexed whenever Gore jumped in the CNN/Gallup 2000 tracking poll.
Nate points to a chart depicting age breakdowns in the Democratic vote share for the last 20 contests surveyed by R2K and PPP. He writes: ”The age breakdowns in Research 2000's numbers are almost always close to "perfect" -- in 20 out of 20 cases, for instance, the Democrat gets a lower vote share from among 30-44 year olds than among 18-29 year olds. PPP's data, on the other hand, is *much* messier -- which is what I think we should expect when comparing small subsamples, particularly subsamples of lots of different races that are subject to different demographic patterns”.
Of course, 18-29 year olds consistently vote more Democratic than the 30-44 group. Is that news? Is 20 out of 20 cases reasonable? Let’s compute the probability that the Democratic share of the 18-29 age group would exceed their share of the 30-44 group in all 20 elections.
In 2008, Obama had 66% of the 18-29 segment and 52% of the 30-44 age group. In 2004, Kerry had 56% and 48%, respectively. So in the last two elections, the Democrats had an average 61% share of the 18-29 age group and 50% of the 30-44 group. Given these shares, the probability is virtually 100% that 20 of 20 polls would give the Democrat a higher share in the18-29 age group than in the 30-44 group.
Assume
a 4% MoE.. Then the probability that 20 of 20 would exceed 50% is .997 ^ 20 =
94%
Share of 18-29 group
MoE 61% 56%
Probability
> 50%
1% 100% 100%
2% 100% 99.8%
3% 99.99% 97.7%
4% 99.70% 93.32%
Nate also finds it strange that in
the last 30 races, Democrats did better among women in all cases. Once again, I
ask, is that news? I will spare you the probability analysis. He also questions the lack of volatility in R2000. It’s
not “noisy” enough for his taste.
“Likewise,
take a look at their Presidential tracking numbers from 2008 (http://www.dailykos.com/dailypoll/2008/11/4).
They published their daily results in addition to their three-day rolling
average ... and the daily results were remarkably consistent from day to
day. At no point, for instance, in the
two months that they published daily results did Obama's vote share fluctuate
by more than a net of 2 points from day to day (to reiterate, this is for the
daily results (n=~360) and not the rolling average). That just seems extremely unlikely -- there should be more noise
than that.
You want noise? OK, Nate, let’s compare the R2K LV tracking
poll to the Gallup RV tracking poll. For Obama, the R2K and Gallup standard
deviations were 1.59% and 2.02%, respectively. The corresponding McCain
volatilities were 1.86% and 1.74%. Obama’s average R2K share was 50.29% and
49.65% in Gallup. Based on these stats, R2K and Gallup are fairly equivalent in
both volatility and average poll share.
Nate and Markos have denigrated exit polls and won’t even discuss Election Fraud. Yet they fabricate faux outrage about an independent polling firm that is not the MSM. Nate was recently hired by the NY Times. Unfortunately, the Grey Lady (“All the News that’s Fit to Print”) does not report Election Fraud. In 2004-2005, Markos locked out posters who sought to present statistical and anecdotal evidence pointing to election fraud. But the Kossacks rebelled. Those “conspiracy nuts” are now allowed to post.
Obama’s recorded share was 52.9%, a 9.5 million margin.
But the True Vote model indicates he had 57.5%, a 22 million margin. Want proof
that fraud cost Obama 13 million? Consider this: The National Exit Poll
required that there be 12 million more returning Bush voters than Kerry voters.
That is not only implausible; it is mathematically impossible. There were
likely 10 million more returning Kerry voters than Bush voters.
Why don’t you write about it in the Times, Nate? Or mention it the next time you get on MSNBC? On the other hand, you better not – if you want to keep that job.
Go to http://richardcharnin.com/ to see the proof. Since the MSM will not review my book, I shall not hesitate to mention it here: “Proving Election Fraud”.
TABLE 1
GALLUP vs. R2K TRACKING POLLS (3-DAY AVERAGE)
GALLUP RESEARCH 2000
|
|
Gallup |
|
Change |
Change |
|
R2K |
|
Change |
Change |
|
|
Obama |
McCain |
Obama |
McCain |
|
Obama |
McCain |
Obama |
McCain |
|
Avg |
49.65 |
42.90 |
0.15 |
-0.15 |
|
50.29 |
42.21 |
0.06 |
-0.02 |
|
Stdev |
2.02 |
1.74 |
0.94 |
0.89 |
|
1.59 |
1.86 |
0.70 |
0.73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1102 |
53 |
40 |
1 |
-1 |
|
51 |
44 |
0 |
0 |
|
1101 |
52 |
41 |
0 |
0 |
|
51 |
44 |
0 |
-1 |
|
1031 |
52 |
41 |
0 |
0 |
|
51 |
45 |
1 |
0 |
|
1030 |
52 |
41 |
2 |
-1 |
|
50 |
45 |
0 |
1 |
|
1029 |
50 |
42 |
-1 |
0 |
|
50 |
44 |
0 |
1 |
|
1028 |
51 |
42 |
1 |
-1 |
|
50 |
43 |
0 |
1 |
|
1027 |
50 |
43 |
-2 |
1 |
|
50 |
42 |
-1 |
2 |
|
1026 |
52 |
42 |
1 |
0 |
|
51 |
40 |
-1 |
0 |
|
1025 |
51 |
42 |
0 |
0 |
|
52 |
40 |
0 |
0 |
|
1024 |
51 |
42 |
1 |
0 |
|
52 |
40 |
1 |
-1 |
|
1023 |
50 |
42 |
0 |
-1 |
|
51 |
41 |
0 |
0 |
|
1022 |
50 |
43 |
-1 |
1 |
|
51 |
41 |
1 |
-1 |
|
1021 |
51 |
42 |
-1 |
1 |
|
50 |
42 |
0 |
0 |
|
1020 |
52 |
41 |
0 |
0 |
|
50 |
42 |
0 |
-1 |
|
1019 |
52 |
41 |
0 |
-1 |
|
50 |
43 |
0 |
0 |
|
1018 |
52 |
42 |
2 |
0 |
|
50 |
43 |
-2 |
1 |
|
1017 |
50 |
42 |
0 |
-1 |
|
52 |
42 |
0 |
1 |
|
1016 |
50 |
43 |
1 |
0 |
|
52 |
41 |
0 |
0 |
|
1015 |
49 |
43 |
-1 |
0 |
|
52 |
41 |
0 |
0 |
|
1014 |
50 |
43 |
-1 |
1 |
|
52 |
41 |
0 |
1 |
|
1013 |
51 |
42 |
0 |
1 |
|
52 |
40 |
-1 |
0 |
|
1012 |
51 |
41 |
1 |
-2 |
|
53 |
40 |
1 |
0 |
|
1011 |
50 |
43 |
-1 |
1 |
|
52 |
40 |
0 |
0 |
|
1010 |
51 |
42 |
0 |
1 |
|
52 |
40 |
1 |
-1 |
|
1009 |
51 |
41 |
-1 |
0 |
|
51 |
41 |
0 |
0 |
|
1008 |
52 |
41 |
0 |
0 |
|
51 |
41 |
-1 |
0 |
|
1007 |
52 |
41 |
1 |
-1 |
|
52 |
41 |
0 |
1 |
|
1006 |
51 |
42 |
1 |
0 |
|
52 |
40 |
0 |
0 |
|
1005 |
50 |
42 |
0 |
-1 |
|
52 |
40 |
0 |
0 |
|
1004 |
50 |
43 |
0 |
1 |
|
52 |
40 |
1 |
0 |
|
1003 |
50 |
42 |
1 |
0 |
|
51 |
40 |
0 |
0 |
|
1002 |
49 |
42 |
1 |
-1 |
|
51 |
40 |
0 |
-1 |
|
1001 |
48 |
43 |
0 |
-1 |
|
51 |
41 |
0 |
0 |
|
930 |
48 |
44 |
-1 |
1 |
|
51 |
41 |
0 |
-1 |
|
929 |
49 |
43 |
-1 |
1 |
|
51 |
42 |
1 |
-1 |
|
928 |
50 |
42 |
0 |
0 |
|
50 |
43 |
1 |
0 |
|
927 |
50 |
42 |
1 |
-2 |
|
49 |
43 |
1 |
0 |
|
926 |
49 |
44 |
1 |
-1 |
|
48 |
43 |
-1 |
0 |
|
925 |
48 |
45 |
2 |
-1 |
|
49 |
43 |
1 |
-1 |
|
924 |
46 |
46 |
-1 |
2 |
|
48 |
44 |
-1 |
1 |
|
923 |
47 |
44 |
0 |
0 |
|
49 |
43 |
0 |
0 |
|
922 |
47 |
44 |
-1 |
0 |
|
49 |
43 |
0 |
1 |
|
921 |
48 |
44 |
-1 |
-1 |
|
49 |
42 |
-1 |
0 |
|
920 |
49 |
45 |
-1 |
1 |
|
50 |
42 |
1 |
0 |
|
919 |
50 |
44 |
1 |
0 |
|
49 |
42 |
0 |
-1 |
|
918 |
49 |
44 |
1 |
0 |
|
49 |
43 |
1 |
-1 |
|
917 |
48 |
44 |
1 |
-1 |
|
48 |
44 |
0 |
-1 |
|
916 |
47 |
45 |
1 |
-2 |
|
48 |
45 |
1 |
-1 |
|
915 |
46 |
47 |
1 |
0 |
|
47 |
46 |
0 |
0 |
|
914 |
45 |
47 |
0 |
0 |
|
47 |
46 |
0 |
0 |
|
913 |
45 |
47 |
0 |
0 |
|
47 |
46 |
0 |
0 |
|
912 |
45 |
47 |
0 |
-1 |
|
47 |
46 |
-1 |
1 |
TABLE 2
ALL POLLS vs. R2K TRACKING
Projections based on Undecided Voter Allocation
Projected Vote
Undecided Voter Allocation
All POLLS 75% 25% Research 2000
Obama McCain Margin Obama McCain Margin Obama McCain Margin
Average 49.87 42.67 7.20 54.34 44.16 10.19 50.33 42.33 8.00
Stdev 2.43 2.43 3.74 2.022 2.022 4.04 1.53 1.93 3.23
Max 54 47 16 59.88 47.63 21.25 53 46 13.00
Pollster Sample Min 44 36 0 50.88 38.63 3.25 47 400 1.00
Marist 804LV 11/03 - 11/03 52 43 9 54.6 43.9 10.8 4-Nov 51 46 5
FOX News 971LV 11/02 - 11/03 50 43 7 54.1 44.4 9.8 3-Nov 51 45 6
Zogby 1201LV 11/01 -
11/03 54 43 11 55.1 43.4 11.8 2-Nov 51 44 7
NBC/WSJ 1011LV 11/01 - 11/02 51 43 8 54.4 44.1 10.3 1-Nov 51 44 7
Research2k 1100LV 10/31 - 11/02 51 44 7 53.6 44.9 8.8 31-Oct 51 45 6
Gallup 2847RV 10/31 - 11/02 53 40 13 57.1 41.4 15.8 30-Oct 50 45 5
Hotline/FD 882LV 10/31 - 11/02 50 45 5 52.6 45.9 6.8 29-Oct 50 44 6
Rasmussen 3000LV 10/31 - 11/02 51 46 5 52.1 46.4 5.8 28-Oct 50 43 7
ABC/WP 2446RV 10/31 - 11/02 54 41 13 56.6 41.9 14.8 27-Oct 50 42 8
CNN 1017LV 10/30 - 11/01 51 43 8 54.4 44.1 10.3 26-Oct 51 40 11
Pew 2587LV 10/30 - 11/01 49 42 7 54.6 43.9 10.8 25-Oct 52 40 12
Marist 543LV 10/29 - 10/29 50 43 7 54.1 44.4 9.8 24-Oct 52 40 12
CBS 1005LV 10/28 - 10/31 54 41 13 56.6 41.9 14.8 23-Oct 51 41 10
FOX News 924LV 10/28 - 10/29 47 44 3 52.6 45.9 6.8 22-Oct 51 41 10
Battleground 1000LV 10/27 - 10/30 49 45 4 52.4 46.1 6.3 21-Oct 50 42 8
Ipsos 831LV 10/23 - 10/27 50 45 5 52.6 45.9 6.8 20-Oct 50 42 8
Pew 1325RV 10/23 - 10/26 52 36 16 59.9 38.6 21.3 19-Oct 50 43 7
Newsweek 882LV 10/22 - 10/23 53 41 12 56.4 42.1 14.3 18-Oct 50 43 7
FOX News 936LV 10/20 - 10/21 49 40 9 56.1 42.4 13.8 17-Oct 52 42 10
CBS/NYT 771LV 10/19 - 10/22 52 39 13 57.6 40.9 16.8 16-Oct 52 41 11
NBC/WSJ 1159RV 10/18 - 10/20 52 42 10 55.4 43.1 12.3 15-Oct 52 41 11
CNN 764LV 10/17 - 10/19 51 46 5 52.1 46.4 5.8 14-Oct 52 41 11
Ipsos 773LV 10/16 - 10/20 50 42 8 54.9 43.6 11.3 13-Oct 52 40 12
Pew Resrch 2382LV 10/16 - 10/19 53 39 14 57.9 40.6 17.3 12-Oct 53 40 13
Pew Resrch 1191LV 10/12 - 10/14 50 40 10 56.4 42.1 14.3 11-Oct 52 40 12
CBS/NYT 699LV 10/10 - 10/13 53 39 14 57.9 40.6 17.3 10-Oct 52 40 12
LAT 1030LV 10/10 - 10/13 50 41 9 55.6 42.9 12.8 9-Oct 51 41 10
Ipsos 1036RV 10/9 - 10/13 48 39 9 56.6 41.9 14.8 8-Oct 51 41 10
ABC/WP 766LV 10/09
- 10/11 53 43 10 54.9 43.6 11.3 7-Oct 52 41 11
Newsweek 1035RV 10/08 - 10/09 52 41 11 56.1 42.4 13.8 6-Oct 52 40 12
FOX News 900RV 10/08 - 10/09 46 39 7 56.1 42.4 13.8 5-Oct 52 40 12
NBC/WSJ 658RV 10/04 - 10/05 49 43 6 53.9 44.6 9.3 4-Oct 52 40 12
CBS/NYT 616LV 10/03 - 10/05 48 45 3 52.1 46.4 5.8 3-Oct 51 40 11
CNN 694LV 10/03 - 10/05 53 45 8 53.4 45.1 8.3 2-Oct 51 40 11
Ipsos 858RV 10/02 - 10/06 47 40 7 55.6 42.9 12.8 1-Oct 51 41 10
Marist 943LV 09/28 - 09/30 49 44 5 53.1 45.4 7.8 30-Sep 51 41 10
AP/GfK 808LV 09/27
- 09/30 48 41 7 55.1 43.4 11.8 29-Sep 51 42 9
CBS/NYT 769LV 09/27 - 09/30 50 41 9 55.6 42.9 12.8 28-Sep 50 43 7
Ipsos 1007RV 09/27 - 09/30 48 45 3 52.1 46.4 5.8 27-Sep 49 43 6
Time 1133LV 09/27 - 09/29 50 43 7 54.1 44.4 9.8 26-Sep 48 43 5
Pew Resrch 1181LV 09/27 - 09/29 49 43 6 53.9 44.6 9.3 25-Sep 49 43 6
ABC/WP 916LV 09/27
- 09/29 50 46 4 51.9 46.6 5.3 24-Sep 48 44 4
CBS/NYT 844RV 09/22 - 09/24 47 42 5 54.1 44.4 9.8 23-Sep 49 43 6
ABC/WP 780LV 09/20
- 09/22 52 43 9 54.6 43.9 10.8 22-Sep 49 43 6
FOX News 900RV 09/20 - 09/22 45 39 6 55.9 42.6 13.3 21-Sep 49 42 7
Ipsos 923RV 09/20 - 09/22 44 43 1 52.6 45.9 6.8 20-Sep 50 42 8
NBC/WSJ 838LV 09/19 - 09/22 48 46 2 51.4 47.1 4.3 19-Sep 49 42 7
LAT 1085RV 09/19 - 09/22 49 45 4 52.4 46.1 6.3 18-Sep 49 43 6
CNN 697LV 09/19 - 09/21 51 47 4 51.4 47.1 4.3 17-Sep 48 44 4
Zogby 1008LV 09/13 -
09/15 47 45 2 51.9 46.6 5.3 16-Sep 48 45 3
Ipsos 1046RV 09/13 - 09/15 45 45 0 51.4 47.1 4.3 15-Sep 48 46 2
CBS/NYT 800LV 09/12 - 09/16 49 44 5 53.1 45.4 7.8 14-Sep 47 46 1
Quinnipiac 987LV 09/11 - 09/16 49 45 4 52.4 46.1 6.3 13-Sep 47 46 1
Newsweek 1038RV 09/10 - 09/11 46 46 0 50.9 47.6 3.3 12-Sep 47 46 1