Wednesday, September 09, 2009

Getting the Description RIght

Examining data in only useful if the data provide accurate reliable information. Many surveys and polls provide "bad" information. Polling on health care has been all over the place. In part, this reflects poor survey design. This article describes some of the problems with health care polling, e.g.,:
Indeed, questions that have asked about "Obama's plan" are particularly egregious violators of the tenets of good polling: As of yet, no such thing as an "Obama plan" exists. So when CNN asked respondents whether or not they "favor or oppose Obama's plan to reform health care" and the NBC/Wall Street Journal polling team asked whether "Barack Obama's health care plan" is a good idea, they were asking respondents to voice an opinion on an imaginary concept.

This is interesting. I would assume that most people who claim to support Obama's healthcare plan are general Obama supporters --- as the specifics of his plan aren't really known.

Even Barack Obama's plan from his website is vague and doesn't give clear numbers-
By the "plan," people most likely think of the key issues Obama addresses in his speeches, and know only that the "plan" involves providing some type of public option for healthcare.

Also, the Republican party tends to spread a lot of strange rumors about what Obama is for and what he is against, perhaps giving people false information about his healthcare ideas.
This is a really good example of how the wording used in a survey can powerfully affect the answers given. When people were asked about a "plan," they probably assumed it was something they should know about, and scraped together any information they had about Obama to voice an opinion.
Post a Comment

Subscribe to Post Comments [Atom]

<< Home

This page is powered by Blogger. Isn't yours?

Subscribe to Posts [Atom]