As I’ve frequently said, statistics is an area which is poorly understood by most people, and as a result, it’s an area which is commonly used to mislead people. The thing is, when you’re working with statistics, it’s easy to find a way of presenting some value computed from the data that will appear to support a predetermined conclusion – regardless of whether the data as a whole supports that conclusion. Politicians and political writers are some of the worst offenders at this.
Case in point: over at [powerline][powerline], they’re reporting:
>UPI reports that Al Gore’s movie, An Inconvenient Truth, hasn’t done so well
>after a promising start:
>
>> Former U.S. vice-President Al Gore’s documentary “An Inconvenient Truth”
>>has seen its ticket sales plummet after a promising start.
>>
>>After Gore’s global warming documentary garnered the highest average per play
>>ever for a film documentary during its limited Memorial Day weekend opening,
>>recent theater takes for the film have been less than stellar, Daily Variety
>>reports.
>>
>> The film dropped from its record $70,333 per play to $12,334 during its
>>third week and its numbers have continued to fall as the film opens in smaller
>>cities and suburbs across the country.
>
>It’s no shock, I suppose, that most people aren’t interested in seeing
>propaganda films about the weather. But the topic is an interesting and
>important one which we wrote about quite a few years ago, and will try to
>return to as time permits.
So: they’re quoting a particular figure: *dollars per screen-showing*, as a measure of how the movie is doing. The thing is, that’s a pretty darn weird statistic. Why would they use dollars/screen-showing, instead of total revenue?
Because it’s the one statistic that lets them support the conclusion that they wanted to draw. What are the real facts? Official box office statistics for gross per weekend (rounded to the nearest thousand):
* May 26: $281,000 (in 4 theaters)
* June 2: $1,356,000 (in 77 theaters)
* June 9: $1,505,000 (in 122 theaters)
* June 16: $1,912,000 (in 404 theaters)
* June 23: $2,016,000 (in 514 theaters)
Each weekend, it has made more money than the previous weekend. (Those are per weekend numbers, not cumulative. The cumulative gross for the movie is $9,630,000.)
But the per showing gross has gone down. Why? Because when it was first released, it was being shown in a small number of showings in a small number of theaters. When it was premiered in 4 theaters, they sold out standing room only – so the gross per showing was very high. Now, four weeks later, it’s showing in over 500 theaters, and the individual showings aren’t selling out anymore. But *more people* are seeing it – every weekend, the number of people seeing it has increased!
The Powerline article (and the UPI article which it cites) are playing games with numbers to skew the results. They *want* to say that Al Gore’s movie is tanking in the theaters, so they pick a bizzare statistic to support that, even though it’s highly misleading. In fact, it’s one of the best performing documentaries *ever*. It’s currently the number seven grossing documentary of all time, and it’s about $600,000 off from becoming number 5.
What was the per-theater (note, not per showing, but per theater) gross for the last Star Wars movie four weeks into its showing? $4,500/theater (at 3,322 theaters), according to [Box Office Mojo][bom]. So, if we want to use reasoning a lot like powerline, we can argue that Al Gore’s movie is doing *as well as Star Wars* an a dollars/theater-weekend basis.
But that would be stupid, wouldn’t it.
[bom]: http://www.boxofficemojo.com/movies/?page=weekend&id=starwars3.htm
[powerline]: http://powerlineblog.com/archives/014530.php
Good Math/Bad Math
The beauty of math; the humor of stupidity.
So: they’re quoting a particular figure: dollars per screen-showing, as a measure of how the movie is doing. The thing is, that’s a pretty darn weird statistic. Why would they use dollars/screen-showing, instead of total revenue?
Ironically, when Brokeback Mountain first came out, some of its opponents claimed that it was unpopular, citing low figures for total revenue. Others correctly pointed out that the low total revenue was due to the fact that the movie was showing in a relatively small number of theatres at the time, and that in terms of dollars/screen-showing it was actually doing quite well.
The point here is that there are different measures of how well a movie is doing, and one is not necessarily better than another. Depends on the question being asked. The problem is not with the statistic being used; dollars per showing is actually rather useful info. The problem is with presenting only that statistic, and leaving out others which are equally important.
Yeah, but the last Star Wars movie sucked.
I’ll admit though that lots of people still went to see it.
Also not surprising that Powerline chose to end their quote from the UPI article immediately before this sentence:
I think that we on the left do a poor job of framing these kinds of criticisms. I realize this is a math blog and it is most pertinent to criticize the misuse of statistics. But what you never see is a blog headline like “Rightwing moonbats claim international conspiracy of scientists is faking atmospheric data.” But that is indeed what moonbat Hindrocket is claiming: the movie that Powerline calls “propaganda” is a scientific popularization that has been OK’d with some minor quibbles by every atmospheric scientist asked. By contrast, spinning statistics to support a weak and irrelevant smear really is quite properly called propaganda. Hindrocket is presumably smart enough to know that, since it would have taken some digging to find just the right stat to report. The most reasonable conclusion is that he’s a liar (I’m shocked, shocked!).
Evolution and global warming are both mainstream scientific fields supported by nearly every expert all around the world. If the slur-term moonbat applied to anyone, surely it applies to someone who believes that a highly distributed process of peer-review is actually controlled by a top-down cabal that is suppressing the real science.
Wednesday Hodgepodge
Further evidence has come to light that the Bush administration cherry-picked the intelligence used to justify the invasion of Iraq:
Iraq WMD red flags ignored, ex-CIA aide tells paper
A former CIA officer says he made repeated efforts to alert t…
In part because statistical abuses are used on both sides of the political spectrum. It isn’t clear that there would be a net gain for the left if statistical knowledge among the general public was increased. Sure the right would lose this Hindrocket person, but the left would lose RFK jr. (who is rather more well known in the real world.)
That’s because “right wing moonbat” is an oxymoron. The analogous insult to “moonbat” for right-wingers is “wingnut” — and certainly plenty of left-wing blog headlines read “Wingnuts claim X”, where X is some unpleasant, dishonest, or absurd opinion.
I’ll forgo additional comments, since I’ve gone way off topic. However, the problem with “wingnut” is that rightwingers don’t find it insulting enough. There’s no law that says I cannot appropriate a term such as “moonbat” and apply it to the same people who obviously think it’s some kind of devastating attack. Hinderaker et al. are moonbats, period. Aside from the purely tautological objection that rightwingers cannot be moonbats, I can’t see other argument that would exclude those who believe that scientists are involved in some kind of all-encompassing, all-powerful conspiracy.
I also note one instance of smear appropriation: I have often heard rightwingers dismissing leftwing conspiracy theorists as “seeing black helicopters”. But the black helicopter myth itself comes from a loony rightwing view of an international conspiracy to eliminate American sovereignty. I think this kind of appropriation is actually pretty effective and I find it disturbing that criticism from my side of the aisle tends to play by a largely imaginary set of formal ground rules about which smears we are allowed to direct at whom.
I have a simple theory: when the right wants the left to listen, they are smart enough to co-opt the rhetoric of the left. That’s why they pose any loss of privilege as “reverse discrimination” and why every polluting company has an office tasked with issuing press releases on their environmental stewardship. When the left wants the right to listen, we should adopt their rhetoric of ridicule and bullying. It’s the only language they understand. We try, but we just suck at it. I think that it wouldn’t be such a stretch to learn and get a little better. “Powerline misuses statistics” is a good topic for this blog, but it isn’t going to get any political legs when posed that way.
Finally, I am assuming without direct evident that Mark CC is about as liberal as I am. Who knows? I completely agree with the point that the “bad math” part of his blog is intended as non-partisan criticism, so this is the wrong forum for my objections. It was just an opportunistic aside.
The best way to frame debates such as this is to avoid the typical political smear tactics used in liberal v. conservative arguments. The honest truth is that the debate in this country has been framed is way so biased toward conservatives that anyone to the left of Augustos Pinochet is considered so far left that it’s not surprising to hear them called communists.
It’s no surprise, really, that someone like Bernie Sanders is called a “socialist”, when what he actually advocates is considered in the rest of the world to be a very mild social democratic program (what used to be called “New Deal liberalism” over here).
The reason for this is that “centrist” people tend to think in terms of “politics as usual”, and autmoatically equivocate conservative and liberal positions. If things are always framed in such a way, we won’t win. Conservatives haven’t won on ideology, as their emphasis on pure (or almost so) laissez-faire capitalism doesn’t jibe with the economic interests of the vast majority of Americans. Instead they use the language of “morals” and “values”, things that in reality vary from person to person but make good buzzwords in political soundbytes. We who today are considered to be on the “left” (and who 40 years would be considered moderate) need our own set of buzzwords to combat the anti-science propaganda spewed the ultra-conservative right.
TylerD: yeah, I agree that it’s good to make rational appeals to moderates, who are now mislabeled as “the left” and Mark CC has done a good job here in the process of pointing out some bad math. But I think there have been plenty of rational appeals and obviously it isn’t enough; hence my frustration.
My other reason to comment (since I just posted I wouldn’t in a comment that is on the moderation queue) is to mention something about the way this blog is set up that is probably affecting other people as well.
Often, scienceblogs times out my login and then my post goes automatically to the moderation queue and in a couple of instances has appeared as “Anonymous.” I think the reason that this does not happen on PZ Myer’s blog is that he only accepts comments from those who are registered. Mark CC may have a strong preference for leaving comments open to non-registered commenters, so this is only a suggestion. It takes just a couple of minutes to register, which is free, and I think that it is not unreasonable to have registration as a precondition of adding a comment.
Yes and no. Certainly things like universal health care were considered more moderate positions 40 years ago, but in other ways society *has* become more liberal (not that that is a bad thing).
Consider things like gay rights. 40 years ago, homosexuals were criminals even in communist countries. Now, even the wingnuts aren’t in favor of criminalizing gays — they just don’t want to let them marry — and 40 years ago legalized gay marriage wasn’t seriously considered even by radicals.
Or consider childbirth outside marriage. In my parent’s generation, it was considered shocking even to liberals to have a child outside wedlock (it was expected that the father of the fetus would marry the mother out of “honor” even if he didn’t love her) — nowadays, I’ve even met Bush supporting women who had children outside wedlock.
PaulC: Yes, but the frustration is rather misplaced. See, it’s not only the tactics conservative PR uses that allows them to be so successful in manipulating the public. It’s the fact that they have almost unlimited access to the primary media of information (or, I should say, disinformation) in this country: television and newspapers. While the former is far worse than the latter, reading or watching news now of days seems like sort of like reading press releases straight from the Pentagon to any rational and informed citizen.
Fox News isn’t the only example available. You can read or watch or listen to any “mainstream” news source and hear the GOP party line repeated almost verbatim (a science related example of this that I personally heard is rather dramatic. During a radio broadcast just before the Dover decision was handed down, the anchor stated “Evolution claims the big bang was an accident, Intelligent Design claims that is impossible.”)
While more honest, independent news sources like Pacifica, Indymedia, Link TV, FSTV, AirAmerica and magazines like The Nation, The American Prospect and our own SEED are growing, they still have nowhere near the influence of established media (due primarily to the fact that they lack the huge amounts of third-party funding and ad revenue that drive it).
The basic point is that the progressive movement, in addition to needing new PR tactics, also needs to expand it’s voice and influence into the mainstream. We certainly can’t rely on Rupert Murdoch to help us there.
Johnathan: Yes, I should have drawn a distinction between economic and social liberalism. Socially I would agree that we have, thankfully, become more liberal. But economically it’s almost as if the combined ghosts of Calvin Collidge and Herbert Hoover have possessed the current Republican administration. Trust me, if this administration cared even remotely as much for it’s everyday bible-thumping supporters as it does for it’s friends in the mercantile class, we’d have a solid constitutional ban on gay marriage and the border would be sealed a wall as high as the Sears Tower, and that’s just for a start.
Uh, I think I now know what problem PaulC was talking about (that last comment was from me).
A good post on the selective reporting tactics. Reminds me of the book that I read some months back titled “How to Lie with Statistics by Darrell Huff”.
Inspired by this one of yours, I made a small post today on some statistic in an Indian magazine. Although it is not about “selective reporting”, it is more about “useless reporting” of seemingly glorious numbers of national importance.
Keep up the good work.
I didn’t see anyone touch on this, but dollar grossed/showing can also be skewed because of the difference between how much each theatre charges for a movie and how big each individual theatre is. An IMAX theatre obviously charges more and seats more than a small room. And the going rate for a movie ticket is very different between places like NYC ($10.50 for a regular ticket) and a small town. That means you can have a vastly expanded audience but a much smaller expansion in dollars grossed.