Pollster.com

Articles and Analysis

 

The Rudy Discrepancy?

Topics: 2008 , Divergent Polls , The 2008 Race

The mysterious result de jour is a bit of a conflict between the most recent USA Today/Gallup and CNN/ORC polls on the national Republican primary horserace result. The Gallup survey has shown Rudy Giuliani leading John McCain by 14 and 13 points on their last two surveys (34% to 20% on the survey released today). Meanwhile, CNN/ORC shows a much closer race, with Giuliani leading by only 3 points last month and 2 points (25% to 23%) now. Both organizations poll over exactly the same period this week, and nearly overlapping periods a month ago. So why the difference?

05-08%20gallup%20and%20cnn.png

Why the difference? I have been looking at the numbers and see no obvious explanation. The sample sizes are relatively small (with a reported margin of sampling error of roughly +/- 5%), but differences in the Giuliani vote are statistically significant, especially given the April-to-May consistency for both polls.

The most important difference between the two polls - as Hotline OnCall points out - is that the Gallup polls asks its Republican primary vote question among all adults that identify or lean Republican, while CNN asks it only of self-described registered voters that identify or lean Republican. I might expect such a difference to work in Giuliani's favor, on the assumption that he might be less popular among the more hard core Republican primary voters. But there are two problems with that theory. The first is that despite the labeling, the percentage of adult respondents that were asked the Republican vote question is only slightly smaller on the last two CNN surveys (40% and 39%) than on the last two Gallup surveys (42% and 43%).

05-08%20sample%20size.png

That result is a little odd, since other pollsters that screen for registered voters who identify or lean Republican tend to ask their Republican primary vote question of a smaller percentage of their samples. Looking at recent surveys that provided comparable details, I get 35% (of the sample asked the Republican primary vote question) for the Pew Research Center, 32% for LA Times/Bloomberg, 31% for Time/SRBI and 30% for the Cook/RT Strategies.

Moreover, if we look at the other results from comparable questions over the last month, the other pollsters that screen for registered voters (including those with effectively tighter screens than CNN) have mostly not shown the race as close as CNN/ORC.

05-08%20recent%20gop.png

Which makes these results a puzzle, except for this general rule of thumb: When very small (even invisible) differences in methodology make big differences in the results, it usually means that the underlying attitudes are not strongly held.

In other words, most Republicans nationally have only begun to consider the candidates, much less who they will support in 2008. So their answers to pollsters are showing great variation. When voters start to make up their minds -- next year -- these results will show more consistency.

 

MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR