(Caveat emptor, but please let me know about bugs or problems)
Tests the assumption in censored regression models that the censoring point is independent of the latent outcome. Requires censoring points to be observed for all units. Example Stata syntax: censoringtestkm y t. Details in the published paper.
Stata do files, help files, and other material to adjust standard errors for clustering using Bias-Reduced Linearization (BRL; Bell and McCaffrey, 2002) or a parametric Moulton (1986) correction factor, as discussed in Angrist and Pischke's Mostly Harmless Econometrics, Chapter 8. Copy the do and help files into your Stata working directory or use Stata's net install command to access them remotely from a web page.
Performs a test for manipulation in the regression discontinuity design when the running variable is discrete. Example Stata syntax: rddisttestk voteshare, threshold(.5) k(.02). Details in the published paper.
Implements censored quantile treatment effects estimation and inference. Suitable for a binary endogenous treatment variable with a binary instrument and a right-censored outcome with a possibly random censoring point. Details in the published paper.
Implements RD quantile treatment effects. Details in the published paper.
To install in Stata, use: ssc install cjive. Implements a cluster-jackknife instrumental variables estimator (CJIVE), eliminating many-instruments bias and providing consistent inference in the presence of clustering. Details in the published paper.
To install in Stata: ssc install testjfe. Performs a test of the identifying assumptions in judge fixed effects designs that allows for heterogeneous treatment effects and accounts for the estimation of judge propensities. Details in the published paper.
Contains a MATLAB file to implement an asymptotically uniformly valid method for constructing simultaneous
confidence intervals for partially identified parameters, example files, and help files. Details in the published paper.
Implements a test of the rank invariance or rank similarity assumption common in treatment effects and instrumental variables models. Example Stata syntax: ranktest y d z s, graph generate(rankbin freqs) bounds taulist(25 50 75) boundvars(uhat qdelta delta). Details in the published paper.
Contains .ado files to implement a method which, under testable assumptions on the joint distribution of potential outcomes, bounds the distribution of treatment effects, example files, and help files. Details in the published paper.
To install in Stata: net install st0435. Implements a Stata package which contains four commands to conduct finite-sample inference in regression discontinuity (RD) designs under a local randomization assumption. Details in the published paper
(Coming soon): Implements exact, finite-sample instrumental variables estimation and inference for a binary endogenous variable and binary instrument. Exact instrumental variables. Details in the preliminary draft.