Thursday, January 21, 2010

Poll: If the Election Were Held Today, Honk if You Like Honking Would Defeat a Dead Person

*
*
*

PRINCETON, NJ -- After peaking at 59% last November,  Honk if You Like Honking's favorable rating continues to fluctuate and now stands at 42% with a margin of error of 58 points. That barely exceeds its 40% unfavorable rating (among the Kurds and the football fans billing themselves as "cheesheads [but, sadly, not "curds"]), and is easily its worst evaluation since the 2008 Democratic National Convention when it was shunned by the Democrats, the Republicans, the Socialists, and the Amish, alike.

Honk if You Like Honking's fluctuating popularity is not unique. President Obama's favorable rating (against which Honk if You Like Honking's rating is measured to make Honk if You Like Honking feel like a tiny grasshopper that even a Buddhist monk wouldn't lose any sleep over sitting on) has declined as well, though it has taken a slightly different trajectory than Honk if You Like Honking's. Polls demonstrate consistently, for example, that President Obama's name recognition quotient remains at historically high levels on every continent (plus the fake continent of Australia), whereas Honk if You Like Honking's name recognition quotient barely extends beyond the patio.

Below is a map of the Honk if You Like Honking name recognition quotient:





























                                                                          X    [you are here]









These data are based on the latest USA/TodayLichtenstein/Tomorrow/Gallup/Giddeyup poll, conducted by James Levine, music director of the Boston Symphony Orchestra, who evidently doesn't know how to conduct a poll, but probably is good at conducting something -- maybe electricity. Honk if You Like Honking's favorable rating has dropped by five or six points each of the last three times Gallup/Giddeyup has updated it, and seems to remain stable when people are left alone.

The source of the decline has varied over time. Honk if You Like Honking's favorable rating dropped significantly among people who read, but it has  remained popular among those who have never heard of it, a steady 73%, which, perhaps is a comment on the veracity of responses given to pollsters who call during broadacasts of "Mad Men."


Survey Methods

Results are based on cell phone interviews with 2.5 national adults (whose phones' batteries, predictably, were about to gasp their last breath at the inception of the interview) . The data from the sample are mushed together, weighted down with heavy stones demographically, and left to dry in the sun for 3 weeks before being released to the public. For results based on the total sample (i.e., 2.5 adults), one can say with 95% confidence that the maximum margin of sampling error is ±99 percentage points. Thus, the data are of virtually no statistical significance.  They do, as it turns out, though, make a very fine Cabernet.

In addition to sampling error, question wording and practical difficulties in conducting surveys can introduce error or bias into the findings of public opinion polls.  For the reported poll, respondents were asked the following question:  "As between getting poked in the eye with a sharp stick and reading Honk if You Like Honking, which would you prefer?"

No comments:

Post a Comment