Replication for R&P Ensemble Forecasting of Irregular Leadership Change
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Replication materials for:
Ensemble Forecasting of Irregular Leadership Change

For questions contact the corresponding author Michael Ward or Andreas Beger.

The complete original PITF report is available on, and contains a large amount of additional information on the method we used for forecasting, accuracy assessments, etc.


Beger, Andreas, Cassy L. Dorff, and Michael D. Ward, 2014, "Ensemble Forecasting of Irregular Regime Change," Research & Politics.

  title={Ensemble Forecasting of Irregular Leadership Changes},
  author={Beger, Andreas, Dorff, Cassy L., Ward, Michael D.},
  journal={Research \& Politics},

Getting the code and data

The easiest way to get the replication code is to download a zip. Alternatively, you can clone the repository through the Github GUI client (OS X, Windows).

The data, including several intermediate results, are available on dataverse:

Running the replication

  1. Download or clone this repository.

  2. Download the 3 data sets on Dataverse and place them in replication/data.

  3. In runme.R, change the working directory path on line 33.

  4. Source or run the code in runme.R. We recommend running through the code block by block rather than sourcing. The original analysis was run on OS X using R 3.0.2 and 3.1.1.

The script relies on two packages, EBMAforecastbeta and spduration that are not available on CRAN. They are included in replication/R/packages with both OS X and Windows versions. The replication script will attempt to install them if they are not already present, but you may have to do so manually if this fails.

See replication.pdf for a list of included files and scripts.