Other packages > Find by keyword >

gausscov  

The Gaussian Covariate Method for Variable Selection
View on CRAN: Click here


Download and install gausscov package within the R console
Install from CRAN:
install.packages("gausscov")

Install from Github:
library("remotes")
install_github("cran/gausscov")

Install by package version:
library("remotes")
install_version("gausscov", "1.1.5")



Attach the package and use:
library("gausscov")
Maintained by
Laurie Davies
[Scholar Profile | Author Map]
First Published: 2019-06-18
Latest Update: 2024-03-04
Description:
The standard linear regression theory whether frequentist or Bayesian is based on an 'assumed (revealed?) truth' (John Tukey) attitude to models. This is reflected in the language of statistical inference which involves a concept of truth, for example confidence intervals, hypothesis testing and consistency. The motivation behind this package was to remove the word true from the theory and practice of linear regression and to replace it by approximation. The approximations considered are the least squares approximations. An approximation is called valid if it contains no irrelevant covariates. This is operationalized using the concept of a Gaussian P-value which is the probability that pure Gaussian noise is better in term of least squares than the covariate. The precise definition given in the paper, it is intuitive and requires only four simple equations. Its overwhelming advantage compared with a standard F P-value is that is is exact and valid whatever the data. In contrast F P-values are only valid for specially designed simulations. Given this a valid approximation is one where all the Gaussian P-values are less than a threshold p0 specified by the statistician, in this package with the default value 0.01. This approximations approach is not only much simpler it is overwhelmingly better than the standard model based approach. The will be demonstrated using six real data sets, four from high dimensional regression and two from vector autoregression. The simplicity and superiority of Gaussian P-values derive from their universal exactness and validity. This is in complete contrast to standard F P-values which are valid only for carefully designed simulations. The function f1st is the most important function. It is a greedy forward selection procedure which results in either just one or no approximations which may however not be valid. If the size is less than than a threshold with default value 21 then an all subset procedure is called which returns the best valid subset. A good default start is f1st(y,x,kmn=15) The best function for returning multiple approximations is f3st which repeatedly calls f1st. For more information see the web site below and the accompanying papers: L. Davies and L. Duembgen, "Covariate Selection Based on a Model-free Approach to Linear Regression with Exact Probabilities", 2022, . L. Davies, "An Approximation Based Theory of Linear Regression", 2024, .
How to cite:
Laurie Davies (2019). gausscov: The Gaussian Covariate Method for Variable Selection. R package version 1.1.5, https://cran.r-project.org/web/packages/gausscov. Accessed 05 Apr. 2025.
Previous versions and publish date:
0.0.1 (2019-06-18 17:30), 0.0.2 (2019-09-11 22:50), 0.0.3 (2020-02-13 19:40), 0.0.4 (2020-08-01 18:20), 0.0.5 (2020-08-28 09:30), 0.0.6 (2020-09-05 11:30), 0.0.7 (2020-09-14 14:00), 0.0.8 (2020-10-21 17:00), 0.0.9 (2020-11-07 14:20), 0.0.10 (2020-11-22 13:40), 0.0.11 (2021-01-13 11:50), 0.0.12 (2021-01-27 17:00), 0.0.13 (2021-02-26 14:30), 0.1.0 (2021-03-28 19:10), 0.1.1 (2021-04-30 10:00), 0.1.2 (2021-12-16 15:30), 0.1.3 (2021-12-19 03:10), 0.1.4 (2022-01-17 09:42), 0.1.5 (2022-02-11 14:40), 0.1.6 (2022-03-14 15:50), 0.1.7 (2022-04-26 17:50), 0.1.8 (2022-06-26 18:50), 0.1.9 (2022-11-12 17:40), 1.0.0 (2022-12-08 11:10), 1.0.1 (2023-01-17 10:40), 1.0.2 (2023-02-02 19:10), 1.0.3 (2023-10-11 21:40), 1.1.0 (2024-02-29 13:22), 1.1.1 (2024-03-04 20:20), 1.1.2 (2024-03-19 17:20), 1.1.3 (2024-05-21 22:20), 1.1.4 (2025-01-28 17:40)
Other packages that cited gausscov R package
View gausscov citation profile
Other R packages that gausscov depends, imports, suggests or enhances
Complete documentation for gausscov
Functions, R codes and Examples using the gausscov R package
Some associated functions: abcql . boston . decode . f1st . f2st . f3st . f3sti . fasb . fdecode . fgeninter . fgentrig . fgr1st . fgr2st . flag . fpval . fselect . fundr . fvauto . leukemia . mel_temp . redwine . simgpval . snspt . 
Some associated R codes: decode.R . f1st.R . f2st.R . f3st.R . f3sti.R . fasb.R . fdecode.R . fgeninter.R . fgentrig.R . fgr1st.R . fgr2st.R . flag.R . fpval.R . fselect.R . fundr.R . fvauto.R . simgpval.R .  Full gausscov package functions and examples
Downloads during the last 30 days
03/0603/0703/0803/0903/1003/1103/1203/1303/1403/1503/1603/1703/1803/1903/2003/2103/2203/2303/2403/2503/2603/2703/2803/2903/3003/3104/0104/0204/03Downloads for gausscov0102030405060708090TrendBars

Today's Hot Picks in Authors and Packages

IGST  
Informative Gene Selection Tool
Mining informative genes with certain biological meanings are important for clinical diagnosis of di ...
Download / Learn more Package Citations See dependency  
leapp  
Latent Effect Adjustment After Primary Projection
These functions take a gene expression value matrix, a primary covariate vector, an additional know ...
Download / Learn more Package Citations See dependency  
gllvm  
Generalized Linear Latent Variable Models
Analysis of multivariate data using generalized linear latent variable models (gllvm). Estimation i ...
Download / Learn more Package Citations See dependency  
nextGenShinyApps  
Craft Exceptional 'R Shiny' Applications and Dashboards with Novel Responsive Tools
Nove responsive tools for designing and developing 'Shiny' dashboards and applications. The scripts ...
Download / Learn more Package Citations See dependency  
whitestrap  
White Test and Bootstrapped White Test for Heteroskedasticity
Formal implementation of White test of heteroskedasticity and a bootstrapped version of it, develope ...
Download / Learn more Package Citations See dependency  
deepdive  
Deep Learning for General Purpose
Aims to provide simple intuitive functions to create quick prototypes of artificial neural network o ...
Download / Learn more Package Citations See dependency  

23,990

R Packages

207,311

Dependencies

64,809

Author Associations

23,991

Publication Badges

© Copyright since 2022. All right reserved, rpkg.net.  Based in Cambridge, Massachusetts, USA