The health care bill
Yes, I will have more to say about the health care bill (maybe Alex will too!). But I recall the passage from Herodotus, where he writes of a group (I can't remember which one) which debates all major policy issues both sober and drunk, both reasonably and full of irresponsible passion. That's not my personal model, nor do I wish to see it in the comments. So I'll wait just a wee bit, and let others get both their celebrating and hand-wringing out of their systems…
The Meaning of Statistical Significance
Science News has a good piece by Tom Siegfried on statistical significance and what it means. Siegfried covers a lot of ground including Ioannidis' argument, Why Most Published Research Findings are False, Oomph versus statistical significance, and the meaning of the p-value. On the latter point, Siegfried writes:
Correctly phrased, experimental data yielding a P value of .05 means that there is only a 5 percent chance of obtaining the observed (or more extreme) result if no real effect exists (that is, if the no-difference hypothesis is correct).
He then explains why a 5% level of significance doesn't mean that there is a 95% chance that the result could not have happened by chance.
All of this is correct but there is another more common error that Siegfried does not address. Suppose that a researcher runs a regression and gets a coefficient on some variable of interest of 5.2 and a p value of .001. In explaining his or her results the researcher says "a effect of this size would happen by chance alone only 0.1% of the time." Now that sounds very impressive but it is also misleading.
In economics and most of the social sciences what a p-value of .001 really means is that assuming everything else in the model is correctly specified the probability that such a result could have happened by chance is only 0.1%. It is easy to find a result that is statistically significant at the .001 level in one regression but not at all statistical significant in another regression with small changes such as the inclusion of an additional variable. Indeed, not only can statistical significance disappear, the variable can change size and even sign!
A highly statistically significant result does not tell you that a result is robust. It is not even the case that more statistically significant results are more likely to be robust.
Now go back to Siegfried's explanation for the p-value. Notice that he writes "Correctly phrased, experimental data yielding a P value of .05…" Almost everything of importance is buried in those words "experimental data." In the social sciences we rarely have experimental data. Indeed, even "experimental data" is not quite right – truly randomized data might be a better term because even so-called experimental data can involve attrition bias or other problems that make it less than truly random.
Thus, the problems with the p-value is not so much that people misinterpret it but rather that the conditions for the p-value to mean what people think it means are really quite restrictive and difficult to achieve.
Addendum: Andew Gelman has a roundup of other comments on Siegfried's piece.
I worry about this
The Russians are not alone in pushing the idea that the next generation of nuclear reactors should have more in common with the small power plants on submarines than the sprawling installations of today.
And this in particular:
The promise of miniature reactors powering homes, offices and schools is still years from being realized. The first Russian design, a pontoon-mounted reactor intended to be floated into harbors in energy-hungry developing countries, is already being built. But most promoters expect small reactors to come online at the end of this decade.
And this:
Some models are tiny. One, for example, would be small enough to fit into a shipping container and would be trucked from site to site, like a diesel generator, except that it would need to be refueled only once every seven years or so.
The opening cost for these "mini-reactors" is expected to run about $100 million. The full story is here.
Solar Furnace
Hat tip: Boing Boing. And here is an interesting interview with Bill Gross of eSolar who argues that information technology and modularity can be used to scale solar furnaces (by using cheaper mirrors combined with IT to focus the mirrors) in a way that panels cannot.
Assorted links
1. Influences on Scott Sumner.
2. Via Chris F. Masse, interview with Guy Kawasaki.
3. The economics of a fundraising concert.
4. Markets in everything, signaling through lipstick edition.
7. The portfolio effect, a continuing series, this time on green consumers.
Markets in everything vending machines in everything
The Passive-Aggressive Release Machine.
The “Passive Aggressive Anger Release Machine” is a machine that allows you break a dish or two until you feel better. All you have to do is insert a dollar, and a piece of china will slowly move towards you until it falls to the bottom and breaks into a million pieces.
Want to do it again? Insert another dollar.
The photo at the link is quite good. For the pointer I thank Chug.
Michael Clemens on the Millennium Village project
It's hard to summarize, so read the whole thing. But he is calling for a closer look at the evidence and the application of RCT [randomized control trial] standards. Here is an excerpt:
First, the fact that a technology has been scientifically proven in isolation–such as a certain fertilizer proven to raise crop yields–does not mean that it will improve people’s well-being amidst the complexities of real villages. Recent research by Esther Duflo, CGD non-resident fellow Michael Kremer, and Jonathan Robinson shows that fertilizer use is scientifically proven highly effective at raising farm yields and farmers’ profits in Kenya. But for complex reasons very few farmers wish to adopt fertilizer, even those well trained in its use and usefulness. This means that this proven technology has enormous difficulty raising farmers’ incomes in practice. The gap between agronomy and development is very hard to cross.
Second, it is not sufficient to compare treated villages to untreated villages that were chosen ex-post as comparison villages because they appear similar. Many recent research papers have shown this conclusively. A long list of studies conducted over decades showed that African and other children learned much more in schools that had textbooks than in schools that appeared otherwise similar but did not have textbooks. Paul Glewwe, Michael Kremer, and Sylvie Moulin evaluated a large intervention in some of the neediest schools in Kenya (ungated version here, published here). Schools that received textbooks were randomly chosen from an initial pool of candidates. The problem: Children did not learn more in the treated schools than in the untreated schools.
Chris Blattman comments.
Fixed price markets in everything
What do you get when you mix unemployment, frugal consumers and Internet boredom?
One possible answer — Fiverr.com, a site that allows you to buy and sell tasks for $5.
The "gigs," all fixed at $5, range from the silly to serious. Among them: sending a nice postcard from Paris, burning a small paper effigy of your enemy, offers for breakdancing lessons, Photoshopping monsters into your family photos, coining that nickname you never got in high school, balloon animal instruction via Skype and even the penning of Italian love songs.
There's a flurry of more practical microtasks, too: CSS microbugging, social marketing, resume revising and PowerPoint editing help.
The company takes one dollar of the five. The full story is here and I thank Daniel Lippman for the pointer. Also via Daniel, here is a story about robots teaching English in South Korea.
Assorted links
1. Critique of mirror neurons.
2. Can animals commit suicide?
3. What changes your life in Ghana?
5. Norms for cell-phone texting.
6. Canadians sleep more in recessions.
7. Anti-sweatshop campaigns: do they harm workers? (looks interesting but I have not read the paper).
How to improve the bill
I won't return to previous ground or the bigger picture questions, but this paragraph struck me:
The second part of the subsidies, estimated to cost $466 billion during the next decade, would limit out-of-pocket expenses for deductibles and co-payments. This help, for individuals with salaries of $27,000 and families with income of $55,000, would be significantly more generous than any version of the legislation Congress has considered.
Cut out or limit the second part of the subsidies, at the very least. I found the article as a whole to be a very useful discussion of which subsidies are contained in the current bill.
Assorted Links
1. More tragedy of the commons. See also here for a great video from 60 Minutes useful for teaching this material.
2. Alan Greenspan's new paper, The Crisis.
3. Larry White talks with Richard Timerberlake about the gold standard in an Econ Journal Watch podcast.
Questions that are rarely asked: why so many retired cops?
JIm Crozier, a loyal MR reader, asks:
Why do cop movies and TV shows so often begin with an older (and often jaded) officer that is just about to retire? It is quite astounding how often this unrealistic plot trick is employed, and the psychological grounding seems weak at best.
I don't have the viewing experience to give you an evidence-based response. I would think the answer might lie in marginal utility theory plus behavioral economics. Perhaps all his life that officer has failed to achieve some desired end, such as catching a criminal, bringing an evil politician to justice, reforming the corrupt police force, or whatever. If the officer is near retirement, we know we are watching a very dramatic story which will define the life and career of that officer for ever and ever. It is harder for the viewer to have the same feeling if the officer has four years, three months remaining on the force. Failure would not mean final failure.
On the behavioral front, our impressions of experiences, and the memories we form, very often depend on what comes last. Judges are more impressed by the group which sings last in the Eurovision contest, even though it is randomized. The viewer thus implicitly knows that the cop really cares about the final segment of his or her career, reinforcing the point about decisiveness and marginal utility.
Viewers, can you do better?
The Rousseauian exodus
Life has come full circle for many Haitians who originally migrated to escape the grinding poverty of the countryside. Since the early 1980s, rural Haitians have moved at a steady clip to Port-au-Prince in search of schools, jobs and government services. After the earthquake, more than 600,000 returned to the countryside, according to the government, putting a serious strain on desperately poor communities that have received little emergency assistance.
The full story is here. The article notes that in the countryside food is growing ever scarcer. Here are two final quotations:
“It’s like you become a Communist here because you never touch money,” she said. “But it’s not so bad. Even though I left 25 years ago, Fond-des-Blancs is still the place that I call home.”
And:
“These three girls were all university students, and now their future is uncertain,” she said. “They don’t know what to do with themselves here. Every morning they wake up and say, “Mama, take us back. We’d rather sleep on the street.’ ”
My review of the new edition of van Gogh’s letters
I read these new volumes in December. There are six large books, two columns to a page, large pages, the whole thing weighs about thirty pounds. I can't recall taking on such a large reading project in such a short period of time, but I am very glad I spent a few weeks immersed in the world of Vincent van Gogh. I was impressed by how smart van Gogh was, what an intellectual omnivore he was, and how well he could compose a letter and pour forth a lot of information very rapidly. The illustrations and footnotes in the volumes are stunning. You'll find the review here. Excerpt:
The collected letters of great creative minds can often be read as lengthy case studies in the dissimulation and the control of one's personal image to others. This is the case with van Gogh, whose writing also shows how such interpretive attempts break down. Some of his letters are practical documents containing very little information, a series of bland platitudes to cajole, influence, and perhaps even mislead their readers. Tone and content contrast strikingly, from one recipient to the next. He himself stated–if only in passing–that there is a lot wrong or exaggerated in his letters, "without my always [sic] being aware of it" (December 23, 1881).
When van Gogh writes to his parents, he sounds like a normal son who is keen to reassure Mom and Dad that everything is OK; with his sister Willemien, he is loving, doting, and domestic, and it feels that he is trying not to remind her of his chaotic life, rather than trying to conceal it. He describes to her the prospect of sharing a room with Gauguin (July 31, 1888), calling him "a very spirited painter." "We'd live together for the sake of economy and for each other's company." A few months later (October 8 and 29), he writes to Theo that Gauguin needs to eat, walk in the countryside with him (Vincent), and "have a screw once in a while": "He and I plan to go to the brothels a lot, but only to study them." The entire Gauguin story is a highlight of the volumes, and in those letters to Gauguin, not to mention to other artists, van Gogh is prickly, difficult, and condescending, playing the role of rival to the hilt.
As for his letters to Theo, these are so full of life that it's easy for the reader to assume that his brother is getting the "real Vincent." But is he? Through much of this period, Theo is supporting van Gogh, either by sending him money, by selling his art (or trying to), or both. Writing to Theo, the artist comes across as whining, manipulative, and in careful control of the flow of information. It's a kind of faux frankness, maybe not untrue but designed to portray a mind in creative ferment and to fit a certain stereotype. There is often first a thanks for money received, a blizzard of reports about what van Gogh is doing and painting, and then at the end a suggestion that even more painting, activity, and creative ferment might be possible if only Theo would do everything to support him. Time and again, the reader wonders just how much van Gogh and his brother trust each other. In the letter of August 14, 1879, for instance, he complains that Theo has advised him to give up his quest to be an artist. "And, joking apart, I honestly think it would be better if the relationship between us were more trusting on both sides," van Gogh suggests, before apologizing for the possibility that so much of the family sorrow and discord have been caused by him. These look and sound like letters to his brother, but in essence we are reading fund-raising proposals.
You have to register to read the whole review but it doesn't take long. www.bookforum.com, by the way, is one of my all-time favorite web sites.
Assorted links
1. Most influential books, chosen by Matt Yglesias.
2. How are prostitute networks different?
3. The influence of J.G. Ballard.
4. The evolution of fairness toward strangers, and here. Important if true, from my hotel room I've just glanced at it but worth a read. It's pro-Hayek and minimizes the influence of evolutionary biology, at least under one reading.
5. One proposal for pricing attention.
6. Jenny Davidson's book list.
7. Unhappy Yemen.
8. Will Wilkinson's book list, including the tale of his unfinished denunciation of me.
9. Webcast of Econblogger's conference, with Alex, Megan, Mark Thoma, others (not me).