exit poll redux

A friend's blog asks which of the following two studies of exit polls should be regarded as reliable:

"this guy says the exit polls couldn't have been off so far by chance" (Stephen Freeman, UPenn)

"these guys say the difference is insignificant" (CalTech/MIT Voting Technology Project)

So, I'm not much of a statistician; I understand some things about probability and I speak a few distributions and so on, but I'm not accustomed to doing confidence analyses. So I'd have to do a lot more scut work to check on the analyses themselves.

Instead, I can provide a higher-level meta-analysis, which might be of interest.

The CalTech/MIT analysis doesn't really give me much confidence in their results: they don't go through their methods, they don't talk about exactly what data they're working with or where they got it from, and they don't really address possible confounding factors very well. The whole analysis strikes me as being kind of shallow, and there isn't enough here for me to be able to check their work. I also have the vague feeling that they basically bought the "exit polls were skewed" argument coming out the door.

By contrast, Freeman's analysis (after a brief skim) seems to have none of these problems. I can't guarantee that he didn't screw something up, but at least I feel that I could back-check him if I wanted to take the time.

Update: Robin has given me permission to post our e-mail discussion about this. I'll be posting my future responses, if any, in the comments.

( Robin's first response to the above, on the nature of the data )

( My recognition of a difference in aims )

( Robin's response to my identification of a dichotomy )

tempting, but no.

http://www.theregister.com/2004/02/03/us_parents_give_birth/

(And no, it's not the same as naming your kid "[your name], II": "the second of this name" is not the same as "a revised version of".)

it's not just environmentally friendly.

http://www.treehugger.com/files/2004/10/solar_vibrator.php

(And no, I don't know why they didn't use that slogan themselves. Oversight, I guess. ;> )

preaching to the echo chamber

The activist organizations that I get email from occasionally encourage people to write letters to the editor on issues of the day.

( one example )

The thing is that I suspect that most people write letters to the editor of the paper that they enjoy reading the most. Which, aside from those people that enjoy being pissed off, tends to be the paper whose bias is most congruent with their own (where there's more than one local paper, anyway). Which means that the people they're talking to are, generally speaking, more likely than not to agree with them.

These are not the people you need to be convincing. If you think that writing letters to the editor is useful at swaying the opinions of readers of that paper, pick the paper whose editorial slant you don't like. Your reception won't be as friendly, but you'll let the readers know that another perspective exists, at least, and might incidentally give heart to the folks in that community that do agree with you, and have been feeling outnumbered.

(I wonder what it feels like to be a dogmatic fundamentalist Republican in San Francisco right now?)

This might have a couple of nice side effects: if you want to do a good job of persuading, then you'll have to consider the perspective of your audience. Which means that you'll be less likely to demonize them in your own mind. While I have enjoyed reading the occasional polemic on the recent election results, getting a bunch of people to reinforce each others' rage with increasingly inflammatory statements is, IMO, ultimately corrosive.

musings on flavors of activism

(Sparked by a posting from red_frog.)

The question: "why does queer in-your-face outness have to be so [overtly sexual]?" (phrasing changed from the original for clarity)

( some complementary thoughts and hypotheses )

( A side note on unanswering questions. )

"Agent Orange" [short film]

http://www.amazon.com/exec/obidos/tg/browse/-/13609401/102-8468033-2291304

Pretty good, as short films go, although I found some of the camera work at the beginning distracting. Involves a rather cool techno remix which uses the most-recognizable bit from La donna e mobile.

(Oh, and I found it amusing that part of the soundtrack involves platform announcements using numbered platforms...which, if this really is the DC Metro (as it appears to be), don't exist at the film location.)

Also one of the most blatantly consumerist films that I've ever seen that purported to not be a commercial. (Amazon, of course, provides links to the stuff shown in the film that they sell.) But hey, you can't have everything.