andrewducker | It's how you ask the question that matters

It's how you ask the question that matters

The New York Times took a poll. They asked half the people whether they thought that gay men and lesbians should be allowed to serve openly in the US army. 60% said yes. They asked the other half whether they thought that homosexuals should be allowed to serve openly in the US army. 44% said yes.

One can only assume that people are made of crazy. And stupid.

From

Flat | Top-Level Comments Only | Expand All

No, you should assume that their views are lightly held, so that a small difference in phrasing will change them.

If their views are so lightly held that a change in phrasing with identical meaning causes them to change them then they are crazy. And stupid.

No, they are not insane, and they are not idiots. They are selfish and disinterested.

Clearly insane. Clearly idiots.

(How long do you think we can keep this up for? Think we can get anyone else to join in?)

Edited 2010-02-12 16:25 (UTC)

This comment makes no sense to me, sorry.

Well, we're both making blanket generalised assertions without anything to back them up, which strikes me as the least useful form of communication ever.

I mean, contradicting something I said without offering any reasoning wasn't going to change my mind, so I assume that it wasn't meant as an actual attempt to do so. Therefore I can only assume that you were doing it for fun, so I was joining in by contradicting you in return. I assumed we were engaging in something like the Monty Python "Argument" sketch.

You weren't being _serious_ were you???

Yes, I was perfectly serious. You don't really think that there is a case of mass insanity, and while you may think that there is a case of mass stupidity, I think that's a very patronising line to take. I consider your explanation a more extraordinary one than mine, and I consider replacing an extraordinary explaination with a less extraordinary explaination a perfectly reasonable thing to do, even without any evidence to follow that up. That is, you'll note, how general hypothesis-forming works; find the simplest, most likely thing.

Aaah. In which case I'd like to say that I wasn't making a diagnosis, nor was I attempting to deduce their actual levels of IQ, I was merely deing disparaging in my despair.

Which in a way, I was responding to as well. I think your despair is misplaced, and it's not as bad as you think!

I shall hope so. I'd rather people were just negligent than having completely incoherent mental models (see also comments below about the humanising effect I think that "gay man" might have on people's reactions).

Uninterested, surely. To be disinterested is a positive quality, akin to being impartial....

(Sorry to nitpick, but that one drives me up the wall)

Are they identical? If you believe that men should be able to serve and women shouldn't, then you'd answer no to the first and yes to the second, wouldn't you? Although I'd expect the figures to skew in the opposite direction based on that.

How big was the answering sample? If there were 100 people in each then it could be simple differences of opinion that only average out as the sample size increases massively.

The national telephone poll was conducted with 1,084 adults Feb. 5-10 and has a margin of sampling error of plus or minus four percentage points for each half sample. Complete poll results and article will be available this evening at www.nytimes.com.

I am a long way from convinced that 1000 people from a population of 100 million is significant to analyse closely. It is only 0.001% of the population or put another way less than five times the number of people reading this post I guess.

I don't see how the population size it's taken from has any bearing on it.

What we're interested in is the chances of them producing such a differential through sheer chance - which will be staggeringly low for a sample size that high.

But that's my point it isn't a high sample size for the population it alleges to represent. Especially if that was half of the 1000 asked each question. Taking the accepted errors into account the difference can be accounted for by only 40 people. What I'm unsure of is if that also allows for wilful 'wrong answers '

Anyway this sample is too small to be more than curious enough to merit further sampling, and it certainly doesn't merit wild accusations of stupidity or insanity on its own.

Sample size is only really all that important if you are wedded to a Fisherian notion of significance. Or in short I think you ay perhaps be arguing at cross purposes with yourself as your overall point seems to be that the result may not be substantively significant (glancing at the numbers I suspect it is a significant result with an impressive power I'd check but am at work and can't really sit in front of SPSS crunching numbers).

Assuming proper randomization then I reckon the power of this sample if probably enough to make generalisations about the wider population.

Dependent on the geographical area sampled of course. Although studies of relatively low sample sizes can be used to make all sorts of valid wider generalisations depending on the statistical tests used.

I'm not entirely clear what you mean by willfully incorrect answers?

Although I agree that the result doesn't merit wild accussations of stupidity or insanity. All it shows is that "homosexual" is a far more loaded term then gay men or lesbians. Or that there was some systematic bias in the way the questions were asigned to participants.

If you get a chance with SPSS I'd appreciate it - meantime thanks!

Fisherian what? I have no idea what you are talking about, but I know enough real human people to know that extrapolating 500 to 100 million simply does not convince.
So how am I arguing against myself when I say that it I don't see it as definitive but it is a curiosity to look deeper at.

Wilful wrong answers refers to something I read about how any survey contains a small proportion of respondents who deliberately give answers opposite to what they think is expected. All I wondered was is this where the 4% +/- error comes from?

(no subject)

endless-psych.livejournal.com - 2010-02-12 21:39 (UTC) - Expand

(no subject)

cheekbones3.livejournal.com - 2010-02-12 22:22 (UTC) - Expand

(no subject)

pigeonhed.livejournal.com - 2010-02-12 23:38 (UTC) - Expand

(no subject)

drplokta - 2010-02-13 07:53 (UTC) - Expand

(no subject)

pigeonhed.livejournal.com - 2010-02-13 10:00 (UTC) - Expand

(no subject)

andrewducker - 2010-02-13 10:38 (UTC) - Expand

Arh, the clasic six sigma question

aberbotimue.livejournal.com - 2010-02-15 16:30 (UTC) - Expand

Erm... 'statistics are like bikinis'.

No, they're really not.

You don't know the quotation or you disagree with it?

I know of several similar ones, so I could work out the rest :->

And yes, I disagree :->

Which is _yes_ you can twist statistics, because so many people don't understand them, so they can't tell when you're fucking with them, but they aren't intrinsically meaningless.

If you don't trust statistics, you should, I imagine, avoid all modern medicine that isn't intuitively obvious.

Got a headache, a rash, an aversion to light and a neck you can't bend without pain? Sticking a needle in your spine hardly seems intuitive. Sure, the statistics say you might well have meningitis, but they're meaningless...

Flat | Top-Level Comments Only | Expand All