Regression Discontinuity Estimation

Provides the tools to undertake estimation in Regression Discontinuity Designs. Both sharp and fuzzy designs are supported. Estimation is accomplished using local linear regression. A provided function will utilize Imbens-Kalyanaraman optimal bandwidth calculation. A function is also included to test the assumption of no-sorting effects.


Version: 0.57:

  • Fixed covariate handling.

Version: 0.56:

  • Fixed bug in plot.RD.

Version: 0.55:

  • Added dependence on Formula.

Version: 0.54:

  • Removed LICENSE to comport with CRAN policy.
  • Renamed VERSION to NEWS.

Version: 0.53:

  • Fixed bug in the estimation of LATEs away from zero.

Version: 0.52:

  • Fixed bug when cutpoint not equal to zero.
  • Fixed bug with sharp RD estimation.

Version: 0.51:

  • Fixed a bug which resulted in crashes of the summary.RD and plot.RD functions.
  • Big changes in the handling of bandwidths.
  • Now accepts a vector of bandwidths as inputs.
  • Some outputs have been modified to reflect this change.

Version: 0.50:

  • Added better error messages. Fixed bug in plot.RDD. Other minor code changes.

Version: 0.42:

  • Submission issue.

Version: 0.41:

  • Fixed submission issue.

Version: 0.4:

  • Made compatible with CRAN.

Version: 0.31:

  • Added plot.RD documentation.

Version: 0.3:

  • Improved plot method, fixed some various bugs.

Version: 0.22:

  • Fixed handling of missing values.

Version: 0.21:

  • Fixed bug in RDestimate when frame=TRUE and no covariates.

Version: 0.2:

  • Added separate function for kernel weights, S3 methods for plotting and summarizing RD objects.

Version: 0.1:

  • First version. IKbandwidth, DCdensity and RDestimate created and working.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.57 by Drew Dimmery, 5 years ago

Browse source code at

Authors: Drew Dimmery

Documentation:   PDF Manual  

Task views: Econometrics

Apache License (== 2.0) license

Depends on sandwich, lmtest, AER, Formula

See at CRAN