A Questionable Poll in Lubbock
Surely they don’t do it this way in Peoria?
To catch you up, a Lubbock TV station reported on a local poll that had Gov. Rick Perry ahead of U.S. Sen. Kay Bailey Hutchison in the Republican primary for governor. Jim Henson, part of the team that does the University of Texas/Texas Tribune Poll, fired off a blog item about it.
He had some questions about the poll, and, it turns out, with good reason.
The poll’s methodology falls somewhere between unorthodox and dubious.
The pollster is a printer. Michael Stevens is running his busy but ...
Comments (4)
jrj
Poll estacado.
txwatcher
Ross, Jim's posting wont allow me to comment for some reason. But is he is flat ass wrong.
Based on the info you provided there is no reason to discount that Lubbock mail in survey then an Internet survey or a telephone survey. The reliability will be about the same. All three methods have issues but the Lubbock survey using a combo of mail and the internet is just as reliable as an opt in web based users or one just calling off a voter list. Jim should know better then to trash a poll base on a new concept. More Intel could shed new light on this but the details known to readers so far do not diminish the results of this survey.
mstevens
At this point we are standing on our record of excellent accuracy. I have contacted Mr. Henson by email and hope to hear from him soon to discuss our polling methods. Mike Stevens
jrhenson
RE: Txwatcher (and mstevens):
Mike Stevens and I are playing email/phone tag after a couple of very friendly email messages from him over the weekend which I didn't get back to until this morning, but just to clarify my late Friday afternoon blog posting: As txwatcher suggests, I should be (and am) the last person to raise questions about the Lubbock poll just because it might be seen as unorthodox, and that wasn't my motivation or intent. My reservations are about the nature of the sample (again, based on what I know at the moment) and it's effect on the results. If the sample included, as Ross's post said, registered voters new to Lubbock, and, more importantly, "voters who took part in “Operation Chaos — a grassroots campaign geared to flood the 2008 Democratic presidential primaries with people who’d vote for Hillary Clinton and against Barack Obama," there is significant potential for non-random bias in the sample. This latter group is particularly unlikely to be a random representation of Republican primary voters, likely or registered voters overall, or the general population, and it seems very likely that it muddies the representativeness of the poll's sample.
So I didn't mean to "trash" the poll, and if came off that way as I used a looser blogging style, my bad. I simply wanted to point to what seem like serious issues with the sampling that would seem to compromise the results and should be taken into consideration in presenting them, which seems like a fair matter of discussion. I look forward to Mike about his polling, because it seems like an interesting enterprise, and he seems like a nice guy besides.