PoSI: Valid Post-Selection Inference for Linear LS Regression

In linear LS regression, calculate for a given design matrix the multiplier K of coefficient standard errors such that the confidence intervals [b - K*SE(b), b + K*SE(b)] have a guaranteed coverage probability for all coefficient estimates b in any submodels after performing arbitrary model selection.

Package details

AuthorAndreas Buja [aut], Kai Zhang [aut], Wan Zhang [cre]
MaintainerWan Zhang <wanz63@live.unc.edu>
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the PoSI package in your browser

Any scripts or data that you put into this service are public.

PoSI documentation built on Jan. 13, 2021, 5:10 a.m.