reverseR: Linear Regression Stability to Significance Reversal
Tests linear regressions for significance reversal through leave-one(multiple)-out and shifting/addition of response values. The paradigm of the package is loosely based on the somewhat forgotten "dfstat" criterion (Belsley, Kuh & Welsch 1980 <doi:10.1002/0471725153.ch2>), which tests influential values in linear models from their effect on statistical inference, i.e. changes in p-value.
| Version: |
0.1 |
| Depends: |
R (≥ 2.13.0), shiny, markdown, knitr |
| Imports: |
DT |
| Published: |
2019-04-24 |
| Author: |
Andrej-Nikolai Spiess
Michal Burdukiewicz
Stefan Roediger |
| Maintainer: |
Andrej-Nikolai Spiess <a.spiess at uke.uni-hamburg.de> |
| License: |
GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| NeedsCompilation: |
no |
| Materials: |
README NEWS |
| CRAN checks: |
reverseR results |
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=reverseR
to link to this page.