More on the Star Tribune

More on the Star Tribune Minnesota poll: The Star Tribune Minnesota poll has a long and inglorious history in Minnesota. Most famously, in 1978 the Minneapolis Tribune (as it then was) called all three major state races wrong by a wide margin on the basis of its Minnesota poll. According to the Tribune on the Sunday before the election, the Democrats were about to sweep the gubernatorial and two Senate races. Instead, 1978 was the year of the “Minnesota massacre.” The Democrats were routed; Republican Al Quie was elected governor, and Republicans Dave Durenberger and Rudy Boschwitz were elected Minnesota’s senators. Following the election, as I recall, the Tribune apologized to its readers, accounted for the errors it had made, and vowed to put its house in order.
I complained a couple days ago about the persistent Republican undersampling in the Star Tribune Minnesota poll. Such undersampling is generally difficult to prove, because election day results that differ from final pre-election poll results can simply be explained away as reflecting post-poll shifts in voter sentiment. In my post on Sunday I referred to the Star Tribune’s final year 2000 pre-election presidential poll results as strikingly discrepant with the actual election results in a way that was inconsistent with every national poll. (The Strib year 2000 Minnesota poll was directed by Rob Daves and employed the same methodology as it does today.) I would now like to review the details.
The Strib’s final pre-election poll results were published on Sunday, November 5. 2000, two days before the election. The story reporting the poll results ran on page one as “Gore takes 10-point lead in state.” The story dramatically reported that in a race that had been neck and neck, Gore had opened a 10-point lead over Bush, 47 percent to 37 percent; the poll had been taken from October 31 to November 3. The story reported that the race was “still-volatile” and quoted University of Minnesota political science professor Steve Smith as saying, “Gore’s in the driver’s seat in Minnesota. It appears a number of Minnesotans came back to Gore–where a lot of people expected them to be all along.” On election day, however, the race was in fact neck and neck; Gore edged Bush in Minnesota by only 60,000 votes out of 2,450,000 votes cast, 47.9 percent to 45.5 percent.
I don’t think the Star Tribune Minnesota poll can have been accurate, and the effect of the poll on Republican voters must have been demoralizing. The remarkable fact about the 2000 presidential election is that Bush’s pre-election lead, measured in every national poll, evaporated in the days before the election. In their post-election recap “Gore’s Closing Surge” in the Weekly Standard (November 27, 2000), “Natonal pollsters are nearly unanimous in believing that a George W. Bush lead of perhaps 5 percentage points at the end of October turned into the dead heat in the popular vote that was cast on November 7.” The article reviewed final shifts in voter sentiment in detail, showing that Gore’s closing surge varied in size around the country; his gains were widespread but not uniform.
I thought at the time, and still do, that the Star Tribune’s final pre-election poll was wrong and probably affected the election result in Minnesota. I called Rob Daves to say as much and to complain about it. I also summarized the Bell and Cannon article that belied the Strib poll results. With no evidence other than his own poll, Daves stated that Minnesota was an exception to the national trend; in Minnesota, Bush had a closing surge.
If I were Rob Daves, I would have been mightily embarrassed by the discrepancy between the final pre-election Minnesota poll results and the election results. When I called Daves, however, he unapologetically defended the accuracy of the poll results, though without the citation of any relevant evidence. I was appalled by his sheer lack of professional introspection in the face of substantial evidence that contradicted his assertions. He was also utterly unconcerned about the impact of his poll on voters even if it was inaccurate.
If I were the owner of the Star Tribune, I would be seriously concerned about the quality of my product. If the Strib’s poll product were edible instead of legible, it would long ago have been recalled as dangerous to human health, or it would have killed off its customers. We can only hope that someday the Star Tribune cares as much about the quality of its news product as McDonald’s does about the quality of its hamburgers.
The problem I have described above persists to this day. The Strib’s Wellstone/Coleman poll published this past Sunday showed Wellstone vaulting into a 47-41 lead after running neck and neck with Coleman for the past several months. I don’t believe it; I think the race remains neck and neck, as the party’s internal tracking polls show, with 10-12 percent of voters undecided. When I called Daves on Monday to reiterate the point I made to him two years ago, he again cited the literature supporting the poll’s methodology. The poll’s methodology employs a weighting of responses for the likelihood that a particular respondent will vote and an adjustment of results for the estimated percentage of eligible voters who are likely to vote. (See the Strib’s description of its methodology quoted below.) I don’t think the Star Tribune has publicly disclosed the bases for whatever weighting and adjustment it applies to its poll results, and they obviously seem to leave much room for error, if not mischief. (Moreover, as I stated on Monday, Daves declined my bet for dinner at a restaurant of his choosing that Coleman would do five points better than the Strib’s final pre-election poll.)
In his conversations with me Daves has generally referred to the accepted social science research that supports the Minnesota poll methodology. Even if the poll’s theoretical underpinnings are sound, however, the evidence of actual election results strongly suggests that the poll errs in practice, consistently, in favor of the Democrats by about five to seven points. It is past time that the Star Tribune is called to account.