Learn R Programming

⚠️There's a newer version (1.2.17) of this package.Take me there.

CorReg (version 0.15.8)

Linear regression based on linear structure between covariates

Description

Linear regression based on a recursive structural equation model (explicit correlations) found by a MCMC algorithm. It permits to face highly correlated covariates. Variable selection is included (by lasso, elasticnet, etc.). It also provides some graphical tools for basic statistics.

Copy Link

Version

Install

install.packages('CorReg')

Monthly Downloads

58

Version

0.15.8

License

CeCILL

Maintainer

Clement THERY

Last Published

November 4th, 2014

Functions in CorReg (0.15.8)

Estimates R2 of each subregression

Probability of Z without knowing the dataset. It also gives the exact number of binary nilpotent matrices of size p.

Curve of the BIC for each possible p2 with a fixed Z and truncature of Z

Estimates B matrix

Imputation of missing values knowing alpha (E step of the EM)

read the structure and explain it

Destructing values to have missing ones

compare signs of the coefficients in two vectors

density_estimation

BIC of estimated marginal gaussian mixture densities

Cross validation

Estimates the response variable using a structure

clean Z columns (if BIC improved)

mixture_generator

Gaussiam mixture dataset generator with regression between the covariates

To compare structures (Z)

Give the partition implied by a structure

clean Z (if BIC improved)

show the missing values of a dataset

To clean Z based on R2

plot and give confidence intervals on the coefficients estimated in a model or for proportions

Compute the BIC of a given structure

Ordinary Least Square efficiently computed with SEM for missing values

Fill the missing values in the dataset

Sparse structure research

compare 0 values in two vectors

Computes the MSE on the joint distribution of the dataset

structureFinder

MCMC algo to find a structure between the covariates

Algorithms for regression with correlated covariates

Upgrades a package to the lastest version on R-forge

compare signs of the coefficients in two vectors

simple MSE function

initialization based on a wheight matrix (correlation or other)

a summary-like function

draws matplot with conditionnal background for easier comparison of curves.

decision tree in a recursive way

Selection method based on p-values (coefficients)

Response variable generator with a linear model