|
According to The Politico, many news agencies are worried that the exit polls may create a false impression over who won the election.
While exit polling is a notoriously inexact science—early exit poll results suggested John Kerry would be elected president in 2004—the introduction of several new variables, ranging from the zeal of Obama’s supporters to his racial background to widespread early voting, is causing concerns among those who charged with conducting the surveys and the networks that will be reporting them...
In theory, exit polls should match election results. But for all the care that goes into conducting accurate exit polls, errant results aren’t completely uncommon. Respected polling analyst Mark Blumenthal found that during the Democratic primaries this year, preliminary exit polls overestimated Obama's strength in 18 of 20 states, by an average error of 7 percentage points, based on leaked early results.
The reason? Obama’s supporters were younger, better educated and often more enthusiastic than Hillary Clinton's, meaning they were more likely to participate in exit polls.
Now I wonder, if this is a problem in exit polls, is it possible that similar problems occur in other polling as well?
Director of Brand Strategy
|
Now I wonder, if this is a problem in exit polls, is it possible that similar problems occur in other polling as well?
I sure hope not! But I've also heard that polling conducted over the phone, which is how Gallup and other major polling organizations gather statistics don't call people on cell phone. This leaves out a huge swath of young (and even older) voters who no longer have land-lines and use a cell phone as their primary number. It has been suggested that a large number of potential Obama supporters (given the younger demographics of his base) have been completely overlooked in polling up to now, and that his actual support is much higher than indicated in polls. So it might be inaccurate either direction.
|
According to The Politico, <snip>
Now I wonder, if this is a problem in exit polls, is it possible that similar problems occur in other polling as well?
That's why reputable pollsters let you see their crosstabs--breakdown by age, their models for likely voter, party affiliation of respondents, etc. The other good indication is trendlines; if the same pollster reports that Candidate A leads Candidate B by 5 points on March 1, and by March 15 Candidate A's lead has increased to 10 points, that's indicative of a real change independent of the model they used. Composite polls are also useful for teasing out model-independent changes.
What you're talking about sounds like a reverse Bradley effect, though--people in favor of a given candidate being reluctant to tell a pollster who they're backing.
Electoral projections (and polling study) done right.
|
|
I like paper ballots. They can be kept and stored for years after the elections are over. These electronic voting machines leave no paper trail. It's easier to rig an election when there's no way to confirm what was actually imputed into the machine.
I live in North Carolina, and our electronic voting machines generate a paper receipt that you can see printing as you enter your votes. It even shows it if you go back and change your vote on a previous screen.
The paper receipt is contained in a starge unit in the machine, so someone in the polling area couldn't pull it off and tear it up either.
I figure that's about as safe (realistically) as voting is going to get unless everyone agrees to electronic voter ID cards.
|
Personally, I've never though much about any kind of polling. It seems to me that it's far too easy for the outcome to be pre-determined (or at least skewed in a certain way). But hey, if they are that worried about exit polls, then the solution is simple - report the actual results as they are made available.