rdmulti 2.0.0

Robust Local Polynomial Methods for RD designs with Multiple Cutoffs or Multiple Scores

Robust Local Polynomial Methods for RD designs with Multiple Cutoffs or Multiple Scores

The package rdmulti implements estimation, inference, and graphical procedures for Regression Discontinuity (RD) designs with multiple cutoffs or multiple scores.

• rdmc: point estimation and robust bias-corrected inference for multi-cutoff designs.
• rdmcplot: data-driven RD plots for multi-cutoff designs.
• rdms: point estimation and robust bias-corrected inference for multi-score designs.

See references for methodological and practical details.

Website: https://rdpackages.github.io/rdmulti.

Source code: https://github.com/rdpackages/rdmulti.

Authors

Matias D. Cattaneo ([e-mail])

Ricardo Masini ([e-mail])

Rocio Titiunik ([e-mail])

Gonzalo Vazquez-Bare ([e-mail])

Installation

To install/update use pip:

pip install rdmulti

Usage

import pandas as pd
from rdmulti import rdmc, rdmcplot

df = pd.read_csv("simdata_multic.csv")

# Multi-cutoff estimation
fit = rdmc(df["y"], df["x"], df["c"])

# Multi-cutoff plot data and figure
plot = rdmcplot(df["y"], df["x"], df["c"])

• Replication: rdmulti illustration, multi-cutoff data, cumulative-cutoff data, multi-score data.

Dependencies

• numpy
• pandas
• scipy
• rdrobust

References

For overviews and introductions, see rdpackages website.

Software and Implementation

• Cattaneo, Titiunik and Vazquez-Bare (2020): Analysis of Regression Discontinuity Designs with Multiple Cutoffs or Multiple Scores.
  Stata Journal 20(4): 866-891.

Technical and Methodological

• Keele and Titiunik (2015): Geographic Boundaries as Regression Discontinuities.
  Political Analysis 23(1): 127-155.

• Cattaneo, Keele, Titiunik and Vazquez-Bare (2016): Interpreting Regression Discontinuity Designs with Multiple Cutoffs.
  Journal of Politics 78(4): 1229-1248.
  Supplemental Appendix.

• Cattaneo, Keele, Titiunik and Vazquez-Bare (2020): Extrapolating Treatment Effects in Multi-Cutoff Regression Discontinuity Designs.
  Journal of the American Statistical Association 116(536): 1941-1952.
  Supplemental Appendix.