Thursday, 18 September 2003

Caple on Colonel Reb Page 2 writer Jim Caple was in Oxford for the ULM game. Shockingly, he had the same reaction to the evocation of Blind Jim Ivy as justification for retaining Colonel Reb that I did:

Plain, old-fashioned college student resentment against an administration making a decision over their heads is a significant part of this. But when [Brian] Ferguson talks about Colonel Reb being a tribute to an old black man named Blind Jim Ivy who sold peanuts around campus during the first half of the century (when blacks weren’t allowed to attend classes), he begins to lose me.

His conclusion:

Colonel Reb is offensive. He has to go.

If his supporters really appreciate the damage Colonel Reb brings to the school and state they love so dearly, they would welcome a new mascot, a mascot that all students can embrace, enjoy and look to with a sense of pride instead of embarrassment.

The state of the art (of polling)

The California Recall has prompted a few questions about various polling techniques. As someone who’s put in his fair share of hours doing telephone survey research, and has heard a version of the “pitch” from Harris Interactive from one of their in-house statisticians*, I thought I’d try to clear up some confusion.

The “traditional” way of doing political polling these days is a system called “random digit dialing.” Basically, to get the number of respondents they need, professional pollsters call several thousand households from a list of residential numbers prepared by companies like Survey Sampling Inc.; if you’re feeling cheap, there are other alternatives that can be used (with a much higher non-response rate). (Before RDD, we did stuff like what Zogby did in Iraq recently; that sort of quasi-random “man on the street” interviewing is common in non-industrialized countries, and essentially the same as contemporary exit polling in the United States.)

RDD worked pretty well for polling until computers arrived on the scene in the mid-80s along with the hardcore telemarketing industry. In the past two decades, response rates have dropped off sharply, requiring more calls to get a valid sample for statistical inference. Coupled with answering machines and caller ID, the effectiveness of RDD for getting a truly random sample has been undermined.

The Internet allows a few new options. Internet survey delivery allows respondents to complete surveys at their own convenience, and also permits the delivery of non-verbal stimuli (like photographs, long blocks of text to be read, and drawings), which is useful for experimental designs. The drawback is that just sticking a survey on the Internet will result in a non-random sample, the most notorious instance of which is the abomination known as the “web poll.” Since respondents to web polls self-select, we have no idea how representative they are of the public at large.

Two groups in the U.S. have tried to tackle the non-random response issue from different directions. Knowledge Networks (KN) solves the representativeness problem by only offering the surveys to a randomly-selected sample of households. Rather than recruiting a new batch of respondents for each survey (like in a traditional phone survey), KN has a rolling panel of several thousand households that participate in studies. They are provided with free WebTV service for the duration of their panel membership, and in exchange must participate in a certain number of surveys. The surveys are delivered via WebTV to the household. (This approach is basically the same as that employed by the Neilsens for television ratings.) As in a traditional phone survey, some weighting is done to adjust the sample to account for stratification and clustering effects. KN’s co-founders are Stanford University professors Norman Nie and Douglas Rivers; Stanford apparently has an arrangement for reduced-cost surveys with KN due to this relationship (at least judging from the number of Stanford professors and graduate students I see at conferences using KN-based experimental and survey data).

The other approach, employed by Harris Interactive, is to do post-hoc adjustments through a technique called “propensity weighting.” Harris has a truly Internet-based panel with a larger membership than KN’s panel (some of the difference in membership size is due to Harris also doing survey work outside the United States; however, they also use bigger samples for each survey for other reasons which I’ll get to shortly). Surveys are administered via the user’s web browser in response to invitations, and participants receive points for participating in surveys and also get entries in regular drawings for cash prizes. Instead of ensuring that participants are representative of the population at large, Harris uses propensity weighting to reweigh respondents based on their demographic and behavioral characteristics and the frequency of those characteristics in the population at large (weighting schemes for other survey techniques are generally based on the design of the sampling procedure). It is important to emphasize that Harris’ technique is not based on random samples. However, propensity weighting is designed to make the sample behave “as if” it was selected randomly.

Which technique is better? All of them have flaws, particularly if trying to reach certain subpopulations like the homeless and indigent (Harris’s technique might find the occasional homeless guy who checks his email at the library; KN and RDD would never catch him). For voting research, however, all of the techniques would probably fare better. Generally speaking participation is correlated with the variables that would be associated with having a telephone, a stable household, and Internet access. To the extent that some population groups are less likely to be online, propensity weighting should adjust for that (in the case of Harris).

Earlier this year, Political Analysis had an article that compared all three techniques, which found that generally RDD, KN, and Harris provided estimates of population parameters within the reported margin of error, with a few notable exceptions. For inferential statistics (trying to figure out the relationships among variables), which is generally what political scientists are interested in, the sampling issues are relatively unimportant, but for the descriptive statistics (trying to figure out what the population-at-large is like) pollsters and the media care about, there may be more important issues that weren’t addressed in the PA piece.

But generally both KN and Harris appear to have credible techniques that have been backed up with actual election results, so their conclusions are as likely to be correct as those of traditional surveys like the Field Poll and L.A. Times.

Idiotic lead graf watch

Today’s winner: the Toronto Star (in fairness, they were only picked on because they were in Google News; I wasn’t planning on continuing the north-of-the-border focus):

WASHINGTON—U.S. President George W. Bush conceded for the first time yesterday that the United States had no evidence indicating Saddam Hussein had anything to do with the Sept. 11 terror attacks.

In related news, I concede for the first time today that I have no evidence that Ben Affleck and Jennifer Lopez plan to get married. Or that they don’t plan to get married. Or that they ever had sex, for that matter.

Vocabulary tip of the day: concession requires the retraction of a previously-held position. For example, Andrew “008” Gilligan conceded that he “sexed up” his own reporting about the alleged “sexing up” of the British government’s mojo-riffic weapons dossier. Bill Clinton conceded that he did have sex with that woman, Miss Lewinsky (although not in quite so few words, or at least not without employing unusual definitions of “is”, “alone”, and “sex”). The United States conceded its claim to British Columbia. Richard Nixon conceded that the United States was no longer interested in defending South Vietnam.

Show me evidence of George Bush claiming that “Saddam Hussein had anything to do with the Sept. 11 terror attacks,” and then you can use the verb concede. Until then, you can use other language, like “reiterated” and “smacked down Dick Cheney for saying stupid things on Meet the Press.”

Then again, this is the country that gave us Alanis Morissette’s definition of “irony,” loosely translated as “anything that sucks ass.” So perhaps I shouldn’t be surprised that “concede” is Canadian for “says something that contradicts something we imagined that the speaker said earlier because it would be consistent with our political belief system.”

Substantive blogging

My copy of Virginia Postrel’s new book, The Substance of Style: How the Rise of Aesthetic Value is Remaking Commerce, Culture, and Consciousness, had shown up in a box on my chair by the time I got to work this morning. I’ve only gotten through the Preface, but it’s been a good read so far. (I would have sat down at one of those nice new tables they have on the rear porch of Weir Hall and read some more, but a half-dozen other people had the same idea I had. They weren’t reading Virginia’s book, though.)

I also watched a bit of the CBC news on Newsworld International this morning—a rerun of last night’s National, with Peter Mansbridge looking appropriately dour, as always. Apparently the Alliance and Progressive Conservatives, Canada’s two main parties of the right, are making another run at a merged organization, tentatively to be named the Conservative Party. I’m not sure that it will fly. The PCs seem to me like warmed over British “one nation” Tories, while the Alliance seem more like the Texas GOP minus the libertarian instincts. More importantly, the Liberals are positioned to capture the median voter in Ontario and Quebec, which is where the votes are anyway under Canada’s system of not-quite-proportional allocation of seats in Parliament. So even if they pull off the grand alliance, I’m not sure it solves much in the long run. (Then again, I’ve been half-expecting Canada to collapse due to its own internal contradictions for the past decade. Of course, states with even less reason to exist, like Belgium, have persisted as well. Blame the Treaty of Westphalia.)

I also learned that a tenth dwarf was added to the presidential race on the Democratic side down here, some guy from Arkansas who apparently is a lot like Howard Dean but spends more time hanging out with war criminals (the latter part I learned from Matthew; Peter didn’t mention that part).

But that story got less play than news that (a) everyone in the media and Parliament is now treating Paul Martin like he’s the prime minister, instead of Jean Chrétien, and (b) Canada’s opening seven more consulates in the United States next year. Amazingly they’ve just gotten around to adding Houston, the fourth-largest city in the United States. Apparently they’re also opening up in a place called “Raleigh-Durham,” which I was under the impression were actually two distinct cities. Then again, so once were Buda and Pest. Or, for that matter, Toronto and Etobicoke.

Dyersburg hostage crisis coverage

Mike Hollihan had running coverage of the hostage situation at Dyersburg State Community College yesterday. Nice job, Mike!

By the way, the current scoring is: Hollihan 1, GoMemphis Blogs 0 (forfeit, they didn’t show up for the event).