en_mp_rows: Computing Elastic Net Estimator when multiple units are...

In susanathey/MCPanel: Matrix Completion algorithms for Causal Panel Data Models

Description

Computing Elastic Net Estimator when multiple units are missing. The underlying algorithm is glmnet package in R. It is worth noting that this package was written by Friedman et. al.

Usage

en_mp_rows(M, mask, num_folds = 5, num_lam = 100L, num_alpha = 40L)

Arguments

M	Matrix of observed entries. The input should be N (number of units) by T (number of time periods).
mask	Binary mask with the same shape as M containing observed entries.
num_folds	Optional parameter on the number of folds for cross-validation. Default is 5.
num_lam	Optional parameter on the number of lambda values (weight penalties). Default is 100.
num_alpha	Optional parameter on the number of alpha values (shape parameter). Default is 40.

Value

The matrix with all missing entries filled.

See Also

cv.glmnet, written by Jerome Friedman, Trevor Hastie, Noah Simon, Junyang Qian, and Rob Tibshirani

Examples

en_mp_rows(matrix(c(1,2,3,4),2,2), matrix(c(1,1,1,0),2,2))

susanathey/MCPanel documentation built on May 29, 2019, 9:51 a.m.