Comments, observations and thoughts from two bloggers on applied statistics, higher education and epidemiology. Joseph is an associate professor. Mark is a professional statistician and former math teacher.
Wednesday, March 21, 2012
Misleading chart of the day
Now examine Aaron Carroll's great rebuttal!
In general, I think Yglesias is correct that it is difficult to have any real reliability for 75 year cost projections (I wonder what the confidence limits are?). So much is likely to change over this period of time and the prioirites of the nation may be so different that it is completely unclear how helpful such an exercise will be. Not only do we have issues with technological and political change, but it would be odd if no future government altered policy priorities or if we could accurately guess economic growth over such a period.
Freakonomics
One piece that I do think is worth reflecting on is this one:
Their first example of a “mistake” concerns a May, 2005, Slate column we wrote about the economist Emily Oster’s research on the “missing women” phenomenon in Asia. Her paper, “Hepatitis B and the Case of the Missing Women,” was about to be published in the Aug. 2005 issue of the Journal of Political Economy. At the time, Levitt was the editor of JPE, and Oster’s paper had been favorably peer-reviewed.
Oster argued that women with Hepatitis B tend to give birth to many more boys than girls; therefore, a significant number of the approximately 100 million missing females might have been lost due to this virus rather than the previously argued explanations that included female infanticide and sex-selective mistreatment.
Other scholars, however, countered that Oster’s conclusion was faulty. Indeed, it turned out they were right, and she was wrong. Oster did what an academic (or anyone) should do when presented with a possible error: she investigated, considered the new evidence, and corrected her earlier argument. Her follow-up paper was called “Hepatitis B Does Not Explain Male-Biased Sex Ratios in China.”I think that this missed the point of what was causing concern with this article. An economist wanders into public health and overturns the conventional wisdom completely by considering a possible predictor but not really understanding why epidemiologists had not considered a disease-based explanation before. It should not be considered a small point that the article showed up in an economics journal and not in a journal where it would be reviewed by experts in the clinical area.
Is this necessary wrong to have reported potentially exciting new results? No. It is also true that people did put the effort into reporting when the understanding changed. But this was in a well developed area of public health with very high policy stakes and people willing to put in a lot of effort to understand if there could be an alternate explanation. So it induces some skepticism about "counter-intuitive" claims in areas where there are not the resources to scrutinize these claims deeply.
Now it is natural that research has an error rate. I wish it did not (especially not my research). But it does point out the hazards of popularizing prelimary results. I think I am especially sensitive to this issue as no field is more guilty of alarming and counter-intuitive findings than pharmacoepidemiology. So I look for clues that make me cautious about publicizing preliminary results before they are really ready for prime time.
Tuesday, March 20, 2012
The Mike Daisey incident illustrates the best in modern journalism
We have always had and will always have people like Mike Daisey, serial fabulists with a gift for self-promotion. We will also always have journalistic sluggards who don't bother to check their facts and derivative hacks who pass on the conventional wisdom without scrutiny or independent thought.
The question is what do we do about these people, and the answer recently has generally been little or nothing. By comparison, the response to the Daisey incident was strong and apt and it gives us a simple template that, if followed, could go a long way toward fixing American journalism.
This is the rule: when you screw up, you take responsibility, try to set the story straight and (here is the essential part) you make your retraction at least as long and at least as prominent as the story you're apologising for.
These days, journalistic malpractice (when not ignored altogether) is generally punished by inclusion in a box that almost no one ever reads on the second page of a newspaper (and even that mild of a penalty is enough to generate whining and self-pity from journalists like David Carr*).
Just imagine what things would be like if errors in front page stories were always followed by front page corrections.
* From Fresh Air
"After I started [at the Times], I quickly ended up on page two ... the Corrections. They're not buried to us; that is a hall of shame ... it's a page you want to totally stay off of ... It doesn't matter where the error occurs — it always follows you around.
"Part of the deal of working at The New York Times is that your readers, a portion of whom are church ladies and copy ninnies and fact freaks, they wait like crows on a wire for you to make the slightest error and then descend, caw, caw, caw-ing, every time you screw up. It still is something that wakes me up at night."
Monday, March 19, 2012
21st century Journalism
This is not consistent with anyone being able to walk up to Foxconn and within two hours be talking to underage workers. The story Daisey tells is one where Apple is negligent to an obvious and easily solved problem, whereas the facts TAL reports are of a company trying to stop underage workers and failing on relatively rare occasions. This kind of lie is not telling the story of the truth through a fictional narrative, but creating a fictional narrative that contradicts the bigger truth.Felix Salmon also has some tough commentary on this issue. The key point here seems to be that it makes a great deal of difference what the facts are. Outright falsehoods are an issue and it is terrifying that such obvious lies passed the fact checkers or that people feel like a defense can be mounted for this behavior as being in "in the greater good" (that the fictional narrative might be exposing hidden truths that are hard to show facts on).
We should do better.
Census documenting Great Depression to be released
NEW YORK (AP) — It was a decade when tens of millions of people in the U.S. experienced mass unemployment and social upheaval as the nation clawed its way out of the Great Depression and rumblings of global war were heard from abroad.Now, intimate details of 132 million people who lived through the 1930s will be disclosed as the U.S. government releases the 1940 census on April 2 to the public for the first time after 72 years of privacy protection lapses.
Friday, March 16, 2012
How our inability to distinguish between independence and contrarianism encourages Steve Landsburg to be, let's just say, a less effective pundit
Noah Smith, Scott Lemieux, my co-blogger and others have done an excellent job addressing the lies and idiocy of this affair (check out how this blogger dismembers the I'm-mocking-the-postion-not-the-person defense) . The question for now is how this happened. How did a mid-level economist manage to reach such national prominence by writing a series painfully sophomoric books and articles?
Part of the answer, I'd argue, lies in the way journalists and editors now treat the counterintuitive. Publications like Slate give us a steady diet of pieces that take some claim that seems obviously true and argue the opposite. These publications would have us believe that this practice is a sign of intellectual independence and healthy diversity of opinion. It's not.
Contrarianism is closer to the opposite of independence, a point that's easiest to explain if we think in the idealized terms of a simplified fitness landscape. and draw an analogy between the defensibility of an argument associated with a certain position and the fitness of a phenotype associated with a certain genotype. (more on landscapes here)
Of course, it would take a lot of variables to realistically describe this landscape but the basic concepts still hold even if we simplify it to a bare-bones x, y and v(x,y). For every position (x,y) you can take, there's a resulting viability (v). Some positions are easy to defend (v is high). Some are difficult (v is low). Pundits and news analysts who try to find the best positions to argue are therefore performing an optimization algorithm (though most probably never thought about it in those terms).
The contrarian approach is to start with a position (x.y) that seems obviously true (often because it is true) then jump to either (-x,y) or (x,-y) and argue from there. It can, at first glance, look like the result of an independent search,but it is actually far more constrained than the neighborhood searches of Frum and Rich. Both of those writers would shift positions based on their reasoning and would insist on finding a defensible point before sitting down to the keyboard.
The typical contrarian piece hews so closely to its initial (-x,y) that there's no indication of a search at all. By all appearances, the writer simply jumps to the contrarian position and starts typing.
Contrarian writing crowds out good journalism and pumps misinformation and faulty arguments into the discourse. This would be bad at any time, but in the current state of journalism, it's disastrous. Here's a list of dangerous trends in journalism from an earlier post (with a link added from a different paragraph):
1. Reliable information sources like the CBO are undermined;All of these factors make it more difficult for our society to deal with bad data and contrarians are a rich source of some of the worst.
2. An increasing amount of our information comes from unreliable subsidized sources like Heritage;
3. Journalists suffer no penalty for publishing inaccurate information;
4. Journalists also fashion for themselves an incredibly self-serving ethical rule that lets them, in the name of balance, avoid the consequences that would have to be faced if they honestly assigned responsibility for screw-ups;
5. A growing tendency to converge on a narrative makes the media easier to manipulate.
In a healthy journalistic system, counter-intuitive claims would be held to a higher standard (at least if we think like Bayesians) and if a logically or factually flawed argument made it through, both the authors and the editors would feel pressure to see that it didn't happen again.
In our current system, counter-intuitive claims are held to a lower standard (because they generate traffic) and serial offenders can actually build careers by badly arguing points that probably aren't true. Editors have lost all interest in fact-checking and outside efforts at debunking are usually treated as he said/she said.
It's easy to object to the positions Landsburg takes, but perhaps the truly offensive aspect here is the way Landsburg and the other contrarians reach those positions.
Thursday, March 15, 2012
Andrew Gelman weighs in
My own take-away is that I had not thought about the intellectual dominance of Freudian thinking for a long time and I had never made the link to economics. But there were occasional forays of economics into areas like education and public health that I have spent some time talking about. By now we all know the idea behind Freakonomics (even if it might be largely a marketing ploy, it has some intelelctual cachet). The issue with Ray Fisman and teacher retention policy (should we fire 80% of new teachers) has seen a lot of discussion on this blog and I consider it a classic example of this type of economics reasoning exported to a more general subject matter. (which is not a dig at Ray Fisman who appears to be a brilliant thinker on his own turf).
So go, read, and enjoy the comments!
Futurism
If we had found better ways to unlock the vast stores of energy that we know are lurking inside the nuclei of atoms, we'd have those flying cars and Mars colonies and everything people thought we'd have back in the 50s (OK, the Economist doesn't say that, but it's true).When did we lose this ambition and can we get it back?
Wednesday, March 14, 2012
Presented without comment
Faced with state funding cuts, Santa Monica College can’t keep up with student demand. The school’s governing board has approved a plan to provide extra classes after the regular ones are full. But while regular classes will cost $46 a unit the extras will be $180.
Addendum
There is still an interesting argument about how modern readers seem to give more weight to counter-intuitive arguments than intuitive ones. Landsberg's career seems to be based on this approach. Bayesian thinking says that we should do the reverse -- and I think that it would be useful to the debate if we remembered such things.
Not thinking like an economist vs. not thinking, like an economist
A lot of people don't get "thinking like an economist" when they see it, [In this case, the people who don't get "thinking like an economist" include Brad DeLong and Noah Smith, but I digress -- Mark*] and what I think Landsburg is doing here is "thinking like an economist", not being a jerk...
Thinking like an economist simply means that you scientifically approach human social behavior - which means that you approach them like any other species of animal. Nobody judges animals when they behave in ways that we would consider horrendous in other humans. They're just... animals. And that's what you really need for good social science. You need to look at your fellow humans as "just animals". Astonishing, wondrous animals to be sure - but just animals...
It's absolutely critical for good economists to see the world in this way...I suspect [Landsburg] was "thinking like an economist". The problem is, of course, it flowed over from scientific analysis of human behavior to a commentary on a single individual human being[.]
[Landsburg] dotted all his i's and crossed all his t's on the analysis, because he's good at thinking like an economist.We've been through this before. Steve Levitt used the thinking-like-an-economist line to dismiss critics. I found it lacking at the time and it hasn't grown on me since then but it should be noted that even at his worst, Levitt is making an effort to approach questions scientifically. I don't believe that a majority (or even a plurality) of Levitt's critics disagree with him because he's too logical, but at least it's a claim that can be made with a straight face.
(for more to this topic, check out this post by Andrew Gelman.)
UPDATE: Daniel Kuehn argues here that Smith misrepresented his original post. Read both and come to your own conclusion.
Tuesday, March 13, 2012
How sure are you that your models are correct?
Now imagine that you withheld a payroll tax cut or food stamp relief or any other program on the basis of fear about long term budgets. Depending on your macro estimates somewhere between millions and hundreds of millions of people suffered for this.
What did you get in return for their suffering?
Absolutely nothing. Nothing. Nothing.
Every time you ask a real living person to suffer for some future goal you have to know that you are betting their well-being on your being right about the future.
How sure are you that you are right?
Austerity costs with probability one. Attempting to effect long term growth is always a gamble.I do think that this point is worth remembering in policy discussions. Models of distant time periods (say 30t o 50 years in the future) are subject to dramatic changes in assumptions. Could the people living in 1890 (who had never seen a plane) have imagined what 1940 (and the air war of the Battle of Britain) would be like?
This is not to say that we should be reckless. But policies like austerity in a time of high unemployment have immediate and real costs. To presume that one is really preparing for the future one should be really, really confident that one can predict it . . .
EDIT: As a clarification, this is much more salient for things like Health Care costs where things like technological progress could completely change the growth curve and less of an issue for Global Warming where we have an observable and deterministic physical process.
Monday, March 12, 2012
And things get worse . . .
The VA system could be turned into a huge asset for our nation's health-care system if it were privatized. One of the big drivers of rising health spending is hospital monopolies: when one or two hospitals dominate a particular region, those hospitals have the power to charge whatever they want to insurers and patients. If civilians were allowed to use VA hospitals, and vice-versa for veterans, we could significantly improve this problem. In addition, if the VA hospitals have indeed come up with operational efficiencies, competing private-sector hospitals would be forced to adopt those efficiencies, or lose patients.So if I think that a single payer model creates efficiency then the way to test that would be to privatize the system so that we could see if it was equally good as a multi-payer system. The things that make a single payer system efficient -- less adminsitrative overhead, rationing, ability to implement cost-effective standards of care, no need to run at a profit -- would all vanish in a competitive market place. Because each insurance plan would have different rules and paperwork requirements which would rapidly undermine a lot of the single payer efficiency.
If liberals are right, and the VA is a model, competition will force private hospitals to improve on both quality and cost. If conservatives are right, and VA hospitals are terrible, privatization would allow veterans to gain access to superior private-sector health care, while increasing provider competition. Seems like a win-win.
So how is abandoning the model used by liberals (single payer) to privatize VA hospitals going to work out as a "win-win"?
The best analogy I can come up with is comparing a privately held company to one that is publicly traded. The idea that the private company should become publicly traded so that one can judge if it is more efficient than the publicaly traded company ignores the possibility that it is more efficient because it is privately held.
So I think that this idea isn't going to show what Mr Roy claims it will show.
Megan McArdle is on hiatus
So the real questionm here is whether MedicAid is worse than no insurance at all. The good folks at the Incidental Economist have a post with a dense series of links as to the complete lack of evidence for this hypothesis.
Now one could argue that it would be nice if MedicAid were better insurance, but that doesn't seem to the concern of the author of the post. Instead, it seems to be about reducing support for health care reform without really positing a superior solution.
UPDATE: It seems that the Incidental Economist addressed this twice, with another post pointing out that reimbursements under MedicAid are set to increase (and that this should increase the number of physicians willing to accept MedicAid).
UPDATE 2: Karl Smith has a rather clever point here on the same piece:
Is the suggestion here that the fixed costs associated with running an office are so high that the breakeven point is achieved from a maximum throughput of full insurance patients? And, further that there is simply no way of operating an office with lower overhead? I can see how its not profit maximizing to accept Medicaid patients. I can even see how in a perfectly competitive market providers would have bifurcate into Medicaid and non-Medicaid providers. However, I do not see why the market cannot find a way to provide paying customers with some level of service.