Kernel Density and Local Polynomial Regression Methods

The package nprobust implements estimation, inference, bandwidth selection, and graphical procedures for kernel density and local polynomial regression methods, including robust bias-corrected confidence intervals.

• lprobust: local polynomial point estimation and robust bias-corrected inference.
• lpbwselect: data-driven bandwidth selection for local polynomial regression.
• kdrobust: kernel density point estimation and robust bias-corrected inference.
• kdbwselect: data-driven bandwidth selection for kernel density estimation.
• plot_lprobust/plot_kdrobust and nprobust.plot: graphical presentation of results.

Python Implementation

To install/update in Python type:

pip install nprobust_pkg

• Help: PyPI repository.

• Replication: nprobust illustration, nprobust data.

R Implementation

To install/update in R type:

install.packages('nprobust')

• Help: R Manual, CRAN repository.

• Examples/data: nprobust illustration, nprobust data.

Stata Implementation

To install/update in Stata type:

net install nprobust, from(https://raw.githubusercontent.com/nppackages/nprobust/main/stata) replace

• Help: kdrobust, kdbwselect, lprobust, lpbwselect.

• Replication: nprobust illustration, nprobust data.

References

For overviews and introductions, see the nppackages website.

Software and Implementation

• Calonico, Cattaneo and Farrell (2019): nprobust: Nonparametric Kernel-Based Estimation and Robust Bias-Corrected Inference. Journal of Statistical Software 91(8): 1-33.

Technical and Methodological

• Calonico, Cattaneo and Farrell (2018): On the Effect of Bias Estimation on Coverage Accuracy in Nonparametric Inference. Journal of the American Statistical Association 113(522): 767-779. Supplemental Appendix.
• Calonico, Cattaneo and Farrell (2022): Coverage Error Optimal Confidence Intervals for Local Polynomial Regression. Bernoulli 28(4): 2998-3022. Supplemental Appendix.

Funding

This work was supported by the National Science Foundation through grants SES-1459931 and SES-1947805.