· A couple of follow-ups to Scott Cunningham’s Mixtape book. First, Thomas Caputo has created python code for the book (to complement the Stata and R code already available). Second, Scott has started a substack he is calling the Remix, which will have deep dives into more methods papers – starting with a discussion of the Callaway and Sant’anna difference-in-differences with multiple time periods paper.
· If you want a nice illustration of when staggered DiD causes issues and discussion of different solutions, video of this talk by Andrew Baker and the associated commentary by Pedro Sant’anna is well worth a watch (as is the point made by the other discussant Edmund Schuster of the importance of theory in helping understand when differential dynamic effects may arise). See also Andrew’s paper and code.
· Tropical deforestation and labor productivity – a new paper in Nature Communications by Masuda et al. looks at the issue of deforestation eliminating the cooling effects provided by trees, and therefore making it hotter and harder to work. They conduct a RCT that randomly assigned 361 workers from rural communities in East Kalimantan, Indonesia to a 90-minute work session in either deforested or forested settings, and also to a standard or a high piece-rate payment schemes tied to worker output. The activity was intended to mimic harvesting work, and involved packing corn into a backpack, carrying it 25 metres, and then unpacking it into a stacked pile, repeating this for 90 minutes. Those in the forested settings were 8% more productive, had lower body temperatures, and took fewer breaks – and doubling incentive pay had no impact on this effect.
· Structured procrastination: “an amazing strategy I have discovered that converts procrastinators into effective human beings, respected and admired for all that they can accomplish and the good use they make of time. All procrastinators put off things they have to do. Structured procrastination is the art of making this bad trait work for you” – one of the best things I read this week while putting off working on things I didn’t feel like working on (via Emilia Tjernström)
· This week Planet Money re-ran the episode it did on the YouWin! business plan competition in Nigeria that I evaluated, together with an update that checked in on how the business owner profiled is doing now.
· Andrew Gelman on how to improve the way you do regression discontinuities – with the provocatively titled “Regression discontinuity analysis is often a disaster. So what should you do instead? – most of the problems arise with a running variable that is not a strong predictor of the outcome, and with fitting functional forms for fitting E(y|z,x) that lack face validity. I'm not so sure on the former, my view is that it is often a power issue and that most polynomial fits look dodgy in RDs.
· Fellowship opportunity to work with our research groups (open until April 30): DEC started receiving applications for the 2021 cohort of the Robert S. McNamara Fellowship. The Fellowship, whose alumni include Dani Rodrik and Shanta Devarajan, was recently restructured. Starting this year, the Impact Evaluation and Development Research departments will host eight young researchers from across the globe to collaborate with World Bank researchers on rigorous, policy-relevant development research.
Join the Conversation