Comments on: If You Disagree, Press 2

By: Carl

Carl — Sat, 27 Feb 2010 15:59:08 +0000

Polls. Yes, No, maybe, and Other. Suggest polls provide the pros and cons
to each poll so the people can make an informed and logical judgement vice the above Yes, No, Maybe, other.
would it make any difference? It might.
Second, I would like to see a sort of Bell Curve dipicting the info by party and news organization input. Something like that.

By: Bri

Bri — Fri, 29 Jan 2010 16:22:29 +0000

When your competitors have a better predictive record than you have, its time to rethink your methodology. PPP is getting it correct. ABC is not.
Simple as that .

By: THWTCO

THWTCO — Fri, 29 Jan 2010 15:34:09 +0000

I don’t trust any net work that spreads hate and discontent by making you look like an idiot if you don’t agree with the Propaganda they demand, if you don’t agree the world is coming to an end. Like the republican Fox net work and they call themselves the Moral Majority spreading hate and discontent, where do They attend church?
I like ABC at least they allow you to disagree, write your opinions most of the time, Thanks

By: Research Rants

Research Rants — Fri, 29 Jan 2010 01:19:56 +0000

Well, I guess it’s a good strategy, in a way, deciding that accuracy doesn’t matter in judging election poll quality. That way, you can just pretend your election polls are the only ones out there, and no one will notice how wildly inaccurate yours are by comparison. Makes sense to me!

By: Gary

Gary — Thu, 28 Jan 2010 21:30:16 +0000

The worst part about this article is I think this guy actually believes what he is saying. I personally will take the polling firm that is accurate most of the time over one that THINKS they have a good methodology. It is like thinking you are the cream of the crop and finding out you are the cream of the crap!

By: anonymous

anonymous — Thu, 28 Jan 2010 19:50:50 +0000

By: Steve

Steve — Thu, 28 Jan 2010 17:00:08 +0000

If accurate predictions of election results aren’t a good independent test for the reliability of various polling methods, then what would be a good test? The argument above is circular (your methods are better because they are your methods): robopolls have methodology problems, but so do live interviewer polls. Rasmussen’s issue polls use obviously biased question wording, and no one should defend them. But PPP is a Dem firm– the attacks on them are mostly blaming the messenger. R. and PPP, and SurveyUSA, have had as good or better predictive value (as scientists say) than live-interviewer polls in recent election. That suggests that the issues confronting live interviewer polls (social desirability bias, in particular) might be worse than the issues confronting robocalls. I wish PPP got different results than they ones they get, and so does Tom Jensen, who runs PPP. But I think his methods have proved their worth.

By: Badger

Badger — Thu, 28 Jan 2010 16:49:08 +0000

“irregardless”? “irregardless”? What the heck is “irregardless”? An erroneous word that means exactly the opposite of what is intended. Get an education!

By: robert

robert — Thu, 28 Jan 2010 16:10:18 +0000

So let me get this straight? You don’t like more accurate robopolls because their samples aren’t in accord with your less accurate live survey polls? Hmm. I’ll have to think about that a bit.

By: ducdebrabant

ducdebrabant — Thu, 28 Jan 2010 15:34:26 +0000

Rasmussen can be a lousy polling organization and still predict “outcomes” accurately, because predicting outcomes is not the largest part of what they do. They have an interest in predictive methodology when they are actually predicting. Most of the time they are doing issue polling; that’s when they get really cute with the methodology because they can. If they weight their poll to prove most Americans think Obama is a citizen of Kenya and born out of wedlock, there’s not going to be a referendum on that issue to expose them. Election predictions are the bait for the public, while all these issue polls are the switch. They’re weighted toward a Republican sample purely to give the impression that Americans have all joined the tea party. As different as the Wall Street Journal’s reporters are from its loony editorial writers, that’s how different its pre-electoral polling is from its issue polling.