- An excellent list of links curated by Masa Kudamatsu, on tips for economists, right through from applying to grad schools to becoming chair of department and Dean (h/t @seema_econ).
- From Unicef, a set of impact evaluations of humanitarian assistance programs (see papers on the right), including supporting the school participation of Syrian children in Lebanon, food assistance in Mali, and programs in Iraq, Yemen and Niger.
- On VoxDev, Karlan, Roth and Mullainathan summarize their work on debt traps – “Even when street vendors are freed from debt and educated about the benefits of saving, they go back to borrowing from moneylenders at exorbitant rates”
- “One of the IVs that has gotten overused in recent years - to the point where it eventually became a punchline - is rainfall”, and “if you have to use IV, stick to linear regression”. Marc Bellemare’s lecture notes on IVs.
Ok, this is an even more specialized blogpost than usual, but I thought it might still be of use to some readers. I’ve received several variants of the following question from colleagues “I’m excited that my AEA session was accepted for the papers and proceedings. But how do I write a P&P paper without hurting my chances of also publishing the longer paper?” or “but the paper I have in that session is already forthcoming somewhere else, what should I write as the P&P?”. I thought I’d offer my advice on this, since there doesn’t seem to be much written out there.
- The Atlantic summarizes a new replication of the marshmallow test, “the new study finds limited support for the idea that being able to delay gratification leads to better outcomes. Instead, it suggests that the capacity to hold out for a second marshmallow is shaped in large part by a child’s social and economic background—and, in turn, that that background, not the ability to delay gratification, is what’s behind kids’ long-term success”
- David Evans’ collection of logframes!
- On the All About Finance blog, Claudia Ruiz and co-authors summarize their work in Peru on using psychometric scoring to extend credit to SMEs – using a regression discontinuity.
- Sylvain Chabé-Ferret hates p-values so much he is writing 6 blog posts about it (post 1, post 2, post 3, post 4, others to come). I particularly recommend post 4, which has a nice illustration of the point that when samples are small, if you find a statistically significant effect, it is heavily biased: in his simulation “With N=100, the estimates that are statistically different from zero at the 5% level are 2 to 2.5 bigger than the true effect”.
- On project syndicate – “Shouldn’t economists ask themselves whether it is morally justifiable to provide even strictly technical advice to self-dealing, corrupt, or undemocratic governments?”
- On Let’s Talk Development, Dan Rogger summarizes some of the latest systems research on the quality of governance; and Bilal Zia summarizes his new paper on how business aspirations are correlated with better small firm outcomes in the cross-section and short panel.
- VoxEU has a new “blogs & reviews” feature – they note that “Very few of the old-style ‘clip and comment’ blogs are still active. On the short and furious end, they have been squeezed by Twitter. On the long, serious end, they have been squeezed by Vox columns and the many Vox-like website that post ‘blogs’..... my idea in launching this new feature is to encourage a much wider range of economists to get into the business of commenting on public policy issues based on their general, research-based knowledge and experience. The essays on this page are far more ‘free form’ than Vox columns. They can be shorter or longer, more technical or more informal.”.
As a change from my usual posts, I thought I’d note five small things I’ve learned recently, mostly to do with Stata, with the hope that they might help others, or at least jog my memory when I unlearn them again soon.
1.Stata’s random number generator has a limit on the seed that you can set of 2,147,483,647.
Why did I learn this? We were doing a live random assignment for an impact evaluation I am starting in Colombia. We had programmed up the code, and tested it several times, with it working fine. In our test code, we had set the seed for random number generation as the date “04112018”. Then when my collaborator went to run this live, it was decided to also add the time of the drawing at the end, so that the seed was set as “041120180304”. This generated an error, and prevented the code from running. Luckily we could quickly fix it, and the live draw proceeded ok. But lesson learned, 2^31-1 is a large number, but sometimes binds.
- NBER Summer institute development economics program and labor studies program.
- The map of “Manuscript-Earth” featuring “The pit of you saved those files, right? Right?”, “confused about the big picture woods”, “The island of misfit results” and other glorious landmarks (h/t Dave Evans).
- Do you say “no” enough to new projects? Anton Pottegard has a nice poster of 8 practical tools to assist in saying no – including JOMO (joy of missing out) – “once a project is turned down, set time aside to actively ponder about how happy you are not to be doing it” (h/t Scott Cunningham).