MatthieuStigler / MCPanel

Matrix Completion Methods for Causal Panel Data Models

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

MCPanel

Matrix Completion Methods for Causal Panel Data Models

The MCPanel package provides functions to fit a low-rank model to a partially observed matrix.

To install this package in R, run the following commands:

install.packages("devtools")
install.packages("latex2exp")
library(devtools) 
install_github("susanathey/MCPanel")

Example usage:

library(MCPanel)
estimated_obj <- mcnnm_cv(M, mask, to_estimate_u = 0, to_estimate_v = 0, num_lam_L = 40)
                  
best_lam_L <- estimated_obj$best_lambda
estimated_mat <- estimated_obj$L

Note: it may be necessary for Windows R 3.4.2 users to use the patched version of R: https://cran.r-project.org/bin/windows/base/rpatched.html

More details will be added soon.

References

Susan Athey, Mohsen Bayati, Nikolay Doudchenko, Guido Imbens, and Khashayar Khosravi. Matrix Completion Methods for Causal Panel Data Models [link]

About

Matrix Completion Methods for Causal Panel Data Models

License:GNU General Public License v3.0


Languages

Language:C++ 97.8%Language:C 1.3%Language:R 0.9%Language:CMake 0.0%