But in many, very important cases, the distribution is not normal. And if we attack the problem is the distribution was normal, we are likely to get it wrong. I may have posted this before, but if anyone hasn't read it, is well worth a read.
Originally Posted by user
"Million Dollar Murray" is an article about power-curve problems. It explains why certain problems--like homelessness or excessive pollution from cars, might be easier to solve, than to manage.
The Salt Lake City area has implemented some of the proposed solutions to chronic homelessness put forward in this article with some fairly good success.
Notably for our audience here, in addition to just general knowledge of social science, is the section dealing with bad cops in the Rodney King era LAPD.
Between 1986 and 1990, allegations of excessive force or improper tactics were made against eighteen hundred of the eighty-five hundred officers in the L.A.P.D. The broad middle had scarcely been accused of anything. Furthermore, more than fourteen hundred officers had only one or two allegations made against them—and bear in mind that these were not proven charges, that they happened in a four-year period, and that allegations of excessive force are an inevitable feature of urban police work. ... A hundred and eighty-three officers, however, had four or more complaints against them, forty-four officers had six or more complaints, sixteen had eight or more, and one had sixteen complaints. If you were to graph the troubles of the L.A.P.D., it wouldn’t look like a bell curve. It would look more like a hockey stick. It would follow what statisticians call a “power law” distribution—where all the activity is not in the middle but at one extreme.
One officer had been the subject of thirteen allegations of excessive use of force, five other complaints, twenty-eight “use of force reports” (that is, documented, internal accounts of inappropriate behavior), and one shooting. Another had six excessive-force complaints, nineteen other complaints, ten use-of-force reports, and three shootings. A third had twenty-seven use-of-force reports, and a fourth had thirty-five. ....
The report gives the strong impression that if you fired those forty-four cops the L.A.P.D. would suddenly become a pretty well-functioning police department. But the report also suggests that the problem is tougher than it seems, because those forty-four bad cops were so bad that the institutional mechanisms in place to get rid of bad apples clearly weren’t working. If you made the mistake of assuming that the department’s troubles fell into a normal distribution, you’d propose solutions that would raise the performance of the middle—like better training or better hiring—when the middle didn’t need help. For those hard-core few who did need help, meanwhile, the medicine that helped the middle wouldn’t be nearly strong enough.
The sections of the article dealing with polluting automobiles and homelessness are also a fascinating read.
This bit of political psycho-analysis near the end of the article is something worth chewing on for many of us as we all run the risk of viewing the world through our preconceived social and political views.
Power-law solutions have little appeal to the right, because they involve special treatment for people who do not deserve special treatment; and they have little appeal to the left, because their emphasis on efficiency over fairness suggests the cold number-crunching of Chicago-school cost-benefit analysis. Even the promise of millions of dollars in savings or cleaner air or better police departments cannot entirely compensate for such discomfort.