Dick Morris: Party Disparities Aren’t Main Cause of Polling Inaccuracy
Veteran pollster Dick Morris who has worked for politicians of both parties has joined the fray in discussing recent polling featuring unusually large numbers of Democrats proportionate to Republicans.
Those polls produce doubtful results, not because they are being skewed to include more Democrats but because they are being artificially skewed to more resemble a 2012 electorate model. While most of the pollsters are refusing to weight their results against a party ID poll, according to Morris they are artificially weighting them according to various age and racial demographics:
But any telephone survey always has too few blacks, Latinos, and young people and too many elderly in its sample. That’s because some don’t have landlines or are rarely at home or don’t speak English well enough to be interviewed or don’t have time to talk. Elderly are overstated because they tend to be home and to have time. So you need to increase the weight given to interviews with young people, blacks and Latinos and count those with seniors a bit less.
Normally, this task is not difficult. Over the years, the black, Latino, young, and elderly proportion of the electorate has been fairly constant from election to election, except for a gradual increase in the Hispanic vote. You just need to look back at the last election to weight your polling numbers for this one.
But 2008 was no ordinary election. Blacks, for example, usually cast only 11% of the vote, but, in 2008, they made up 14% of the vote. Latinos increased their share of the vote by 1.5% and college kids almost doubled their vote share. Almost all pollsters are using the 2008 turnout models in weighting their samples. Rasmussen, more accurately, uses a mixture of 2008 and 2004 turnouts in determining his sample. That’s why his data usually is better for Romney.
But polling indicates a widespread lack of enthusiasm among Obama’s core demographic support due to high unemployment, disappointment with his policies and performance, and the lack of novelty in voting for a black candidate now that he has already served as president.
If you adjust virtually any of the published polls to reflect the 2004 vote, not the 2008 vote, they show the race either tied or Romney ahead, a view much closer to reality.
The trick is, of course, that 2012 is not going to have an electorate like 2004 or 2008. It’s almost certainly going to be somewhere in-between the two when it comes to demographics. While the pollsters out there may claim they don’t wish to be “unscientific” by referencing party identification, they are already violating pure statistical mathematics by correcting their results against race and age.
Morris then goes on to discuss the 1980 election, the last time a Democratic president was defeated in a general election. Instead of quoting him here, I will turn instead to Jeffrey Lord at the American Spectator who has an in-depth look at the polling before the Ronald Reagan-Jimmy Carter matchup. As it turns out, of nine states which the New York Times polled before the election which it believed were “close,” literally every single one of them ended up going for Reagan, contrary to the Times’s expectations:
In a series of nine stories in 1980 on "Crucial States" -- battleground states as they are known today -- the New York Times repeatedly told readers then-President Carter was in a close and decidedly winnable race with the former California governor. And used polling data from the New York Times/CBS polls to back up its stories. [...]
What we have is the liberal "paper of record" systematically presenting the 1980 Reagan-Carter election in 9 "Crucial States" as somehow "close" in five of the nine -- Texas, Illinois, Ohio, Florida and Michigan. New York was in the bag for Carter. Only in his own California and New Jersey was Reagan clearly leading.
The actual results had only New York "close" -- with Reagan winning by 2. Reagan carried every other "close" state by a minimum of 6 points and as much 17 -- Florida. Florida, in fact, went for Reagan by a point more than California and about 4 more than New Jersey.
Not having a crystal ball, we cannot say that a similar scenario will not happen in 2012 for Romney but all of the above is useful to keep in mind whenever one sees liberal journalists going ga-ga over a poll result showing their beloved Barack Obama ahead in the race.