Learn R Programming

EAlasso (version 0.1.0)

Simulation Based Inference of Lasso Estimator

Description

Simulation based inference of lasso estimator. It provides several methods to sample lasso estimator: (a) Gaussian and wild multiplier bootstrap for lasso, group lasso, scaled lasso and scaled group lasso, (b) importance sampler for lasso, group lasso, scaled lasso and scaled group lasso, (c) Markov chain Monte Carlo sampler for lasso, (d) post-selection inference for lasso. See Zhou, Q. and Min, S. (2017) for details.

Copy Link

Version

Install

install.packages('EAlasso')

Monthly Downloads

9

Version

0.1.0

License

GPL (>= 2)

Maintainer

Seunghyun Min

Last Published

September 1st, 2017

Functions in EAlasso (0.1.0)

Lasso.MHLS

Compute lasso estimator
MHLS

Metropolis-Hastings sampler for lasso estimator under the fixed active set.
PB.CI

Provide (1-alpha)% confidence interval of each coefficients
PBsampler

Parametric Bootstrap sampler for lasso, group lasso, scaled lasso or scaled group lasso estimator
Postinference.MHLS

Post-inference for lasso estimator
cv.lasso

Compute K-fold cross-validated mean squared error for lasso
print.MHLS

Print Metropolis-Hastings sampler outputs
summary.MHLS

Summarizing Metropolis-Hastings sampler outputs
hdIS

Compute importance weights for lasso, group lasso, scaled lasso or scaled group lasso estimator under high-dimensional setting
plot.MHLS

Plot Metropolis-Hastings sampler outputs