Everyone loves polls! But unfortunately, not everyone understands polls, how they work, and what kinds of standard parameters can routinely be used to bias their results. For example, consider this recent poll by Rasmussen Reports that attempts to gauge voter preference for various politicians in the upcoming 2004 presidential election.
September 2, 2003--As a Presidential candidate, Senator Hillary Clinton attracts more Democratic votes than other contenders but still trails President Bush 48% to 41%.Anyone familiar with political polling will recognize one huge problem right off the bat: political telephone polls should never ever be taken on weekends. Why not?
If the Democrats nominate Senator John Kerry, the President leads 45% to 36%. Against Vermont Governor Howard Dean, Bush leads 45% to 34%. Senator Kerry formally announced his candidacy earlier today.
The national telephone survey of 1,499 Likely voters was conducted by Rasmussen Reports August 29-September 1, 2003. Margin of sampling error is +/- 3 percentage points with a 95% level of confidence. Rasmussen Reports measures the economic confidence of consumers and investors on a daily basis. As part of this process, we measure, employment, job satisfaction, interest rates, and more.
So I called one of my old polling friends, Republican Ed Goeas, who worked with me years ago in Christine Todd Whitman's tax-cutting 1993 gubernatorial victory in New Jersey. Along with Democrat Celinda Lake, Goeas publishes the highly-regarded Battleground Survey. He told me to be careful about reading the polls. For one thing, it really matters if polls are conducted during the week or over the weekend. He told me that "political pollsters don't poll on the weekends. They prefer Sunday night through Thursday night. Weekend results are just not reflective of where a given race really is."So the results of the poll I linked to above are basically worthless. Not only was the poll taken on a weekend, but it was taken on Labor Day Weekend -- certainly any standard weekend effects will be amplified during one of the biggest vacation periods of the year. Such a significant choice of dates can't have been a mistake, and I doubt I'll trust anything put out by Rasmussen Reports in the future.
Goeas explained that more Democrats are found at home on the weekends, especially blue-collar Democrats. He added that "anyone who spends 20 to 30 minutes during the weekend talking to some pollster is not normal."
(Link to poll via Drudge.)