Subject:
|
Re: A Berkeley Study That Portrays Liberalism Positively?!!
|
Newsgroups:
|
lugnet.off-topic.debate
|
Date:
|
Wed, 22 Mar 2006 17:14:17 GMT
|
Viewed:
|
1603 times
|
| |
|
|
In lugnet.off-topic.debate, Timothy Gould wrote:
| |
--SNIP--
| |
| |
I read about this on a certain Other Forum and basically said “eh.”
|
lol For the record, I signed up again with yet another email addy, and was
summarily nuked; they must checking IPs. I have officially given up life in
the underground. Pity.
|
????
|
That’s an inside joke between Mr. Neal and me. Nothing to do, incidentally,
with discussions of the UN Embassy in Denmark, which we have all “let go.”
| |
| |
| |
It’s a too-small sample size from a too-small geographic area. I’d say
it’s close to meaningless, and in any case the factors of adolescent life
and parental leanings likely weigh more upon one’s political destination
that does one’s own “whininess.”
|
Agreed.
|
Disagree. One hundred people is a decent amount (error is proportional to
1/sqrt(sample size)). Besides, if the sample size was considered inadequate
in a statistical sense by the experts in the field who review the paper then
it would not have been published.
|
I don’t know about that last part, but a sample of 2,000 kids growing up in a
famously liberal region of California seems to be inviting sample-error.
Chances are good that if you sample 2,000 kids in Beijing, you’ll find that
close to 100% of the whiny ones grew up to be Chinese. Is there a correlation?
Sure. Is it significant? Probably not. Does that mean that a similar
proportion of whiny kids in Sweden will grow up to be Chinese?
At best, this study shows correlation in a limited geographic region. Even if
the sample-number is adequate to describe the trend (of which I’m still not
convinced), the geographic distribution is inadequate except as a commentary
upon the sampled region itself.
Now that I think of it, though, did I misread? Was the sample taken from the
Berkeley area or not? If not, then I may be in error...
| |
| |
What bothers me
most about this (to Tim as well) is it assumes that people are cast somehow
in their political viewpoints. Doesn’t make sense to assume that, it seems
to me.
|
What it says is that about 7% of a persons political viewpoint has a
correlation with their personality. Which seems reasonable to me.
|
Well, no kidding! But correlation of a subjective trait is too nebulous to be a
useful predictor. “Whininess” is too vague a factor IMO to be usefully (ie.,
consistently, objectively) gauged.
| |
The fact that the article actually discusses this is why I said it’s a pretty
good science article. It’s rare to see any mention of the REAL statistical
conclusions.
|
Sort of like the semi-apocryphal story that Eisenhower (it was him, wasn’t it?)
being shocked when he learned that half of all Americans are of below-average
intelligence.
Dave!
|
|
Message has 1 Reply:
Message is in Reply To:
18 Messages in This Thread:
 
  
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
