Replication Page for "Case Selection and the Study of Judicial Politics", with Jeffrey Lax
With the data and code described below, researchers can replicate our results. Note that all the files referenced below, including csv versions of the datasets, can be found in this zip file.
The non-compliance puzzle discussed in the paper is based on the data analyzed in Klein and Hume's 2003 paper, "Fear of Reversal as an Explanation of Lower Court Compliance." This dataset is available here.
The analyses in remainder of the paper are based on the data used in Songer et al's 1994 paper, "The Hierarchy of Justice: Testing a Principal-Agent Model of Supreme Court-Circuit Court Interaction." (Note that the data used in a Klein and Hume paper is a subset of this data). The base version of this dataset is available here. As explained in the paper, we then appended five copies of this dataset together, which we then used to run our simulations. That dataset is available here.
Stata Do-Files and Datasets for Analysis
With the data in hand, we then programmed simulations in Stata, creating one do-file for each selection strategy analyzed in the paper:
Running each of these do-files produces a new dataset of 1,000 observations, 1 for each simulation. The datasets we used in the paper are below. Note that if you re-run the do-files, the resulting dataset will be slightly different to the random draws utilized in the simulations.
R Code for Analyses in Paper
Finally, with the simulated data at hand, we analyzed it using R, which we used to construct all the graphs that appear in the paper. Complete code is available here.