R Modules
Wild bootstrap for bias corrected inference in RD designs with optimal bandwidth selection
- Parallelized R code for calculating wild bootstrap bias-corrected confidence intervals in sharp RD designs. For example uses see my Econometrics Journal article with Maxim Pinkovskiy and the replication kit below.
- It’s a fork from Otávio Bartalloti’s, Gray Calhoun’s and Yang He’s excellent R code. I have added support for cluster sampling, covariates, different distributions for the wild weights, different bandwidths on the left and right, bandwidth selection using the new version of rdbwselect, and parallel computation.
Conley standard errors for massive data sets (on Github but still undocumented)
- Parallelized Rcpp/C++ code for computing Conley errors. Can be used on panels and cross-sections. Works with lm() and lfe() objects. I use it on cross-sections of Kenyan census data with > 1 million observations.
- It’s a fork from Darin Christensen and Thiemo Fetzer’s excellent package. I added the implicit parallelization with RcppParallel and generalized the program to add some flexibility.
- Superseded by fixest package (does all this and more)
Stata Modules
- To install the software type the following at Stata’s dot prompt:
net install fhetprob, from(https://www.richard-bluhm.com/stata/)- To get the example data and pdf documentation (installs in current directory):
net get fhetprob, from(https://www.richard-bluhm.com/stata/)- Then type
help fhetprobor readfhetprob.pdffor usage instructions.
Replication Data for Papers
Top lights: Bright cities and their contribution to economic development
- GeoTiff Images of the Corrected Lights here
- Code (plz ask if needed)
The spread of COVID-19 and the BCG vaccine: A natural experiment in reunified Germany
- Full replication set on Github
Fueling conflict? (De)Escalation and bilateral aid
- Stata code for estimating dynamic ordered probit models with endogeneity and quasi fixed-effects/CRE is available in the JAE replication archive.