The Republican noise machine has been making much of recent polling by partisan polling outfits showing Tom Cotton with a wall lead over Mark Pryor in the race for U.S. Senate.
Latest was Impact Management, led by former Arkansas Republican Party officials, who gave Cortton a 4-point lead in a poll short of black voters and with questions emphasizing Obamacare before they got around to the horse race question with which most polls might have been expected to begin.
Others suggest caution..
The New York Times’ statistical bunch notes here the problems with polling nowadays.
The rapid growth of partisan polls has contaminated the polling averages in states where surveying public opinion is already difficult. Many of these partisan polls employ dubious weighting and sampling practices. The combination will make it even harder for polls to nail the result.
Hmmm. Who do you suppose they could be talking about? Why, yes, Arkansas.
The possibility that partisan polls could skew the averages is perhaps best illustrated in Arkansas, where partisan polls are breaking along predictably partisan lines.
But …. while Cotton leads all but one of the Republican polls and Pryor leads ALL the Democratic polls, the non-partisan polling breaks 4-2 Pryor and the two are from Rasmussen, widely viewed as Republican leaning.
These polls wouldn’t be so problematic if we could simply ignore them and focus on nonpartisan polls. But the five nonpartisan ones conducted so far this year haven’t offered much clarity, with a net 16-point margin separating the most extreme findings.
The two findings most friendly to the Republican nominee, Tom Cotton, were from Rasmussen, while the two news media-sponsored live-interview surveys offered results that looked like potential outliers, showing Mark Pryor, the Democratic incumbent, with a large lead among registered voters. Not even the Pryor campaign’s own poll showed him so far ahead.
The fairest interpretation is that Mr. Pryor holds a slight lead in the polls, since he has an edge in the best nonpartisan polls conducted so far. But this assessment comes with low confidence, given the small number and wide variance of the nonpartisan polls.
Josh Marshall at Talking Points Memo picks up the same theme. He concludes:
So, without putting too fine a point on it, the Dem-leaning ‘partisan’ polls seem right in line with the non-partisan polls. They actually seem to trail them in showing the extent of Pryor’s lead. It’s really Dem-leaning polls and non-partisan polls on one side and Republican polls on the other.
Not every race is going to be like this certainly. And just eye-balling it, it’s a little hard for me believe he’s quite as far ahead as NBC/Marist seems to show. But still. This data set doesn’t really capture what it purports to show and I think the pattern – that this is more an issue with Republican pollsters than Democratic ones is very real.