New package for extreme value analysis in Stata

One topic I’m studying for my main client, the Open Philanthropy Project, is the risk of geomagnetic storms. I hadn’t heard of them either. Actually, they originate as solar storms, which hurl magnetically charged matter toward earth, jostling its magnetic field. Routine-sized storms cause the Auroras Borealis and Australis. Big ones happen roughly once a decade (1972, 1982, 1989, 2003, a near-miss in 2012…) and also mostly hit high latitudes. The worry: a really big one could send currents surging through long-distance power lines, frying hundreds of major transformers, knocking out power to continent-scale regions for months or even years, and causing an economic or humanitarian catastrophe. My best assessment at this point is that if one extrapolates properly from the available modern data, the risk is much lower than the 12%-chance-per-decade cited by the Washington Post last summer. But that’s a preliminary judgment, and I’m not a seasoned expert. And even if the risk is only 1%, it almost certainly deserves more attention. More from me on that in time. (For a mathematician’s doubts about the 12% figure see Stephen Parrott.) You can see “geomagnetic storms” beneath Cari Tuna’s elbow in this photo from a recent Post story about the Open Philanthropy Project: Geomagnetic storms constitute an extremely rich topic, encompassing (ha ha) solar physics, geophysics, the fundamentals of electromagnetism, dendrochronology, power system dynamics, transformer engineering…and statistics. The statistical question is: given the historical data on the severity and frequency of geomagnetic disruptions, what can we say about the probability per unit time of one at or beyond the frontier of historical experience? And that leads into the branch of statistics called extreme value theory. I think of it this way. A...

The domestic economic impacts of immigration

My client GiveWell, working closely with the foundation Good Ventures through the Open Philanthropy Project, is seriously considering labor mobility as a cause to which Good Ventures should commit resources: It appears to us that moving from a lower-income country to a higher-income country can bring about enormous increases in a person’s income (e.g., multiplying it several-fold), dwarfing the effect of any direct-aid intervention we’re aware of. But there are worries: Does letting more workers into a wealthy country take jobs from people already working there? Or does the competition for jobs reduce wages all around? These possibilities are a particular concern as they apply to low-skill workers, who are poorer. For due diligence, GiveWell hired me to review the evidence on the potential side effects of immigration. Here is my full report, ready for comments from anyone. To read my conclusion, skim down to the bullet points. The immigration policies of wealthy nations could be prime leverage points for Good Ventures. “Observably identical” people—ones with the same education, age, sex, and so on—earn 2.0–15.5 times more in the United States than in poor countries such as Peru, Haiti, Egypt, and Yemen (Clemens, Montenegro, and Pritchett 2008). Allowing more low-income foreigners to work in wealthy nations could therefore raise their incomes more than almost any other step that governments or philanthropists can take.1 But there is a concern: Does allowing more immigration take jobs from people already in the labor force of the receiving country? Or does it depress their pay? This document performs due diligence on this question, especially as it pertains to low-skill workers in the receiving...

The impact of life-saving interventions on fertility

My client GiveWell, which is working closely with the new foundation Good Ventures, commissioned me to review the scientific evidence on the impact of deaths on births. When a life is saved, especially a child’s life, do families go on to have fewer additional births than they otherwise would? Is the effect more than one-to-one or less? As I write just below, a criticism sometimes thrown at life-saving interventions is that they do as much harm as good by accelerating population growth. At GiveWell’s request, I am posting the full review here in draft, for public exposure and critique. We see public circulation at this stage as an efficient way to get this analysis as good as we can. So if you disagree with any of it, please let me know by e-mail or by commenting below. Please share this with others who might be interested. The review mixes analysis with (I hope) pedagogic explanations of the strengths and weaknesses of different study designs. At the bottom are two tables, one summarizing my interpretations of the studies, one listing sources. The preliminary conclusion is rather intuitive: I think the best interpretation of the available evidence is that the impact of life-saving interventions on fertility and population growth varies by context, above all with total fertility, and is rarely greater than 1:1 [meaning that averting a death rarely causes a net drop in population]. In places where lifetime births/woman has been converging to 2 or lower, family size is largely a conscious choice, made with an ideal family size in mind, and achieved in part by access to modern contraception....