One of the most amazing — and significant — statistics of this election season has gone almost completely unnoticed:
It has become increasingly difficult to contact potential respondents and to persuade them to participate. The percentage of households in a sample that are successfully interviewed – the response rate – has fallen dramatically. At Pew Research, the response rate of a typical telephone survey was 36% in 1997 and is just 9% today.
The general decline in response rates is evident across nearly all types of surveys, in the United States and abroad. At the same time, greater effort and expense are required to achieve even the diminished response rates of today. These challenges have led many to question whether surveys are still providing accurate and unbiased information.
You read that correctly: In any attempted poll or survey, only 9% of attempted contacts come back with an actual response.
That means 91% of sampled households are NOT having their opinions recorded by pollsters.
Breaking down the numbers a bit, we can see that this is due to two reasons: 38% of the households contacted were unreachable in the first place, leaving only a 62% “contact rate.” But among that 62%, only 14% “cooperated” with the pollsters; the remaining 86% of contactees presumably slammed down the phone or simply refused to answer. Since 86% of 62% of the population are non-cooperators, that leaves us with the astonishing conclusion that…
53% of Americans actively refuse to answer poll questions.
The real breakdown chart should look like this:
38% could not be reached
53% were contacted but actively refused to answer
9% cooperated and answered the polling questions
Or, put another way:
Out of every 7 people contacted by pollsters, only 1 will answer the polling question, while the remaining 6 refuse to answer.
Six to one, people; six to one. Think about that for a second.
What are those 53% thinking — and why would they purposely refuse to cooperate with pollsters?
Furthermore, where are those unreachable 38%? At work? On drugs? Curled up in a fetal position under the couch?
Pew goes on to claim that, despite the appallingly low cooperation rate in 2012, they think their estimates of public opinion are fairly accurate in any case.
That may have been true in past years, but we won’t know this year until after the election how accurate the polls were.
But now also consider these newly released stats showing that distrust of the media has hit an all-time high, and most importantly that Republicans and independents are twice as likely to distrust the media as Democrats:
There’s only one possible conclusion to reach: That the non-cooperating 86% of contactees are twice as likely to be Republicans and independents as they are to be Democrats.
This imputes a HUGE skew into all poll results, a skew that is rarely acknowledged.
Who are the 91%???
Are you one of them?
Did you miss a call from a pollster because you were at work?
Did you refuse to answer a question from a pollster, once contacted?
If so, why did you refuse?
Even if you don’t answer poll calls, do they record your non-response as support for Obama anyway?
We have the stats. Now let’s flesh them out with some anecdotes.
Here’s a summary of some of the anecdotes and reasons for non-response from the comments section below; the number preceding each line is the number of commenters who cited that rationale:
28 – I do answer, but I often lie and give false answers, just to screw with them.
24 – I have caller ID and never answer any call from any number that is either unknown or blocked.
17 – I do not respond because I suspect that callers identifying themselves as “pollsters” are more likely telemarketers, fraudsters or deceptive political operatives engaged in “push-polling.”
16 – I do not respond because of potential privacy violation, that pollsters can correlate my answers with my identity; “I fear that they will use my political beliefs against my family.”
14 – I do not cooperate because I consider the polling industry an arm of the biased media, trying to influence the electorate.
13 – I only answer calls from people I already know; if I accidentally answer a robo-call or a call from a stranger, I just hang up.
11 – I refuse to divulge any personal opinions or data to an anonymous stranger, who could be ill-intentioned for all I know.
10 – “Why should I waste my time talking to these people who will skew the results anyway?”
7 – I’m among the 38% “unreachable” because I do not have a landline.
5 – I’d only cooperate with pollsters if they compensated me for helping them.
4 – It’s just a waste of time; I have better things to do with my life.
4 – I would answer calls from any pollster which I recognize from caller ID as being unbiased, but otherwise I don’t.
3 – I suspect that if I answer once, my number will be added to lists of positive respondents, precipitating more calls.
2 – After I burst out laughing when questioned if I supported Obama, the pollster hung up on me.
2 – I never used to answer pollsters, but recently I have started answering, to counter the inaccuracies in earlier polls.
1 – I hang up if I “don’t like the questions.”
1 – I decline to answer because if I say I’m not voting for Obama they will sneer at me as a racist.
1 – I don’t answer because I think that polls are a corrupting influence on public policy, that political decisions are based on poll results, not on what is actually best for the country.
1 – A pollster questioned me once. I ate his liver with some fava beans and a nice Chianti.
6 – I refuse to cooperate with pollsters for all of the reasons above.