Cell phones causing skewed polls?

[Aroura]

So, the last few days, I've been trying to reconcile the polls, which mostly show Romney in the lead, or at best, tied with Obama. All the news stations are calling it a dead heat. But 538, Intrade, and every bookie in the country is in favor of Obama, and as a matter of fact, Romneys betting odds for winning have only gotten worse over the last 4 or 5 days.

I realize that it is possible to win electoral votes and lose the popular vote, and that may happen. However, other less formal forms of polling show Obama with a decent lead in the popular vote as well, and those are often more correct than polls.

Why is that?

Then yesterday, I was reading an article about polls and cell phones.

The vast majority of official polls are call based, and they call few (and sometimes no) cell phones, let alone other communication devices. In the last 4 to 6 years, (I think specifically, this trend has really accelerated in the last few years, so may not have been experience to this degree in any previous elections), a Large number of Americans have completely given up using land lines, and now use cell or other mobile device only for communication.
Can you guess who makes up the majority of this wireless demographic? Younger people, who we all know tend to lean left. Also the more educated, again, tend to lean left.

Is it possible that phone polls are simply reaching an older, more likely to lean right demographic, and that is skewing the polls by 5 or more points? I think it is VERY possible.

I don't see much coverage of this as an issue in the news, so I could be completely wrong, but it would explain the vast discrepancy we are seeing in official phone polls vs. bookies and/or other unofficial polling methods.

What do you think?

[Minimalist]

Polls are most likely reaching people who answer the phone. When mine rings the first thing I do is check Caller ID. If it is not identified or someone I don't know I let it go to voice mail. If it is important they will leave a message.

You know who answers the phone? Old people.

[festive1]

I had a door to door pollster come by the other day, but that was a local issue. I don't answer numbers I don't know. I figure, if they want to reach me they'll leave a message.

[Tino]

Aroura,

The cell phone issue is well known within the polling industry. You might like to read this piece http://pollingmatters.gallup.com/2012/10...lving.html by Frank Newport, who runs the Gallup poll, considered by many to be among the best. It discusses how they've integrated cell phone polling. This paragraph is particularly relevant:

As we began this election tracking program on Oct.1, our methodologists also recommended modifying and updating several procedures. We increased the proportion of cell phones in our tracking to 50%, meaning that we now complete interviews with 50% cell phones and 50% landlines each night. This marks a shift from our Gallup Daily tracking, which has previously been 40% cell phones. This means that our weights to various phone targets in the sample can be smaller, given that the actual percentage of cell phones and cell-phone-only respondents in the sample is higher. We have instituted some slight changes in our weighting procedures, including a weight for the density of the population area in which the respondent lives. Although all Gallup surveys are weighted consistently to census targets on demographic parameters, we believe that these improvements provide a more consistent match with weight targets. The complete statement of survey methods is included at the end of each article we publish at Gallup.com.

[Ryantology]

Why 50/50? There are more cell phones in the U.S. than people to use them. 90% of Americans use them. Polls should be, at the very least, 90/10 in favor of cell numbers.

[Aroura]

Why 50/50? There are more cell phones in the U.S. than people to use them. 90% of Americans use them. Polls should be, at the very least, 90/10 in favor of cell numbers.

Correct. This would make the polls more accurate than "weighting", which as another way of saying correcting the faults in polls by bets guessing.

On Nov 6th, I'm very curious to see if they have indeed kept up with the fast pace of technology.