Package {HDBRR}

Type: Package
Title: High Dimensional Bayesian Ridge Regression without MCMC
Version: 1.1.5
Description: Implements Bayesian ridge regression for high-dimensional data without using Markov chain Monte Carlo (MCMC). Posterior computations are performed using singular value decomposition (SVD) or QR decomposition. The package also provides variable selection and prediction methods.
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
Depends: R (≥ 3.0.0)
Encoding: UTF-8
Imports: numDeriv, parallel, bigparallelr, bigstatsr, graphics, stats
NeedsCompilation: no
LazyData: true
Config/roxygen2/version: 8.1.0
Packaged: 2026-09-22 17:00:20 UTC; estel
Author: Blanca Monroy-Castillo [aut, cre], Paulino Perez-Rodriguez [ctb], Jose Crossa [ctb], Sergio Perez-Elizalde [aut]
Maintainer: Blanca Monroy-Castillo <blancamonroy.96@gmail.com>
Repository: CRAN
Date/Publication: 2026-09-23 09:30:20 UTC

High Dimensional Bayesian Ridge Regression without MCMC.

Description

Ridge regression provide biased estimators of the regression parameters with lower variance. The HDBRR ("High Dimensional Bayesian Ridge Regression") function fits Bayesian Ridge regression without MCMC, this one uses the SVD or QR decomposition for the posterior computation.

Usage

HDBRR(y, X, n0 = 5, p0 = 5, s20 = NULL, d20 = NULL, h = 0.5,
    intercept = TRUE, vpapp = TRUE,npts = NULL,c = NULL,
    corpred = NULL, method = c("svd","qr"),bigmat = TRUE, ncores = 2, svdx = NULL)

Arguments

y

The data vector (numeric, n) NAs allowed.

X

Design Matrix of dimension n x p.

n0, p0

n0/2 and p0/2 are the shape parameter of the Gamma Inverse prior assigned to the residual variance and the shape parameter of the Gamma Inverse prior assigned to the Beta's variance respectively. The default value for n0/2 and p0/2 parameter is 5.

s20, d20

(n0s20)/2 and (p0d20)/2 are the scale parameter of the Gamma Inverse prior assigned to the residual variance and the scale parameter of the Gamma Inverse prior assigned to the Beta's variance respectively. The default value for the s20 and d20 is NULL. If the scale is not specified a value is calculated with h and quantiles.

h

(numeric, 0<h<1) shrinkage factor. Only used if the hyper-parameters are not specified; If h -> 0 then we have greater shrinkage, this is, \beta -> 0. If h -> 1 then we have less shrinkage.

intercept

Logic value. The default value for the intercept is TRUE.

vpapp

Logic value. Compute an approximation of the predictive variance. The default value for the vpapp is TRUE.

npts

Number (integer) of points used to evaluate the u's density for the numeric aprroach. The default value for the npts parameter is 200.

c

ratio of Gaussian densities (Spike/Slab) in the prior mixture density of each Beta for variable selection.

corpred

The method for the compute of the correlation, there are two methods, Empirical Bayes ("eb") and Bayesian ("b") method. The default value for the parameter corpred is NULL. If the values is NULL then the corr and edf values will be NULL.

method

Options for the posterior computation. There are two methods available: "qr" decomposition of X*t(X) and "svd" decomposition of matrix X. The default value for the method is SVD decomposition.

bigmat

Use of the bigstatsr package. The default value for bigmat is TRUE.

ncores

Number of the cores for computation. The default value for the ncores is 2, you can detect your number of cores with detectCores() and use it (iOS and Linux).

svdx

It is possible to add the svd. The default value es NULL.

Details

Ridge regression is a useful tool to deal with collinearity in the homoscedastic linear regression model providing biased estimators of the regression parameters with lower variance than the least square estimators. The model

y = X\beta + \epsilon

where \epsilon vector is assumed Normal with mean vector 0 and covariance matrix \sigma^2 I_n. For further details see the vignettes in the package.

Value

List containing the following components:

betahat

Vector (numeric, p) with the betas estimates.

yhat

Vector (numeric, n) with the y's estimates.

sdyhat

Vector (numeric, n) with the standard deviation of the predicts values.

sdpred

Vector (numeric, n) with the standard deviation of predict variances.

varb

Vector (numeric, p) with the beta's variance.

sigsqhat

Value (numeric) of the residual variance estimate.

sigbsqhat

Value (numeric) of the Beta's variance estimate.

u

Vector (numeric, npts) with the u's values.

postu

Vector (numeric, npts) with the values of the u posterior.

uhat

Value (numeric) of u estimated.

umode

Value (numeric) of the posterior mode of u.

whichNa

Value (integer) of NAs in the y vector.

phat

Vector (numeric, p), selection probability of x_i.

delta

Used in the variable selection.

edf

Value (numeric) of the effective degrees of freedom for regression.

corr

Vector (numeric, n) of the correlation between y_i estimates and y_i.

svdx

The svd decomposition.

Author(s)

Sergio Perez-Elizalde, Blanca E. Monroy-Castillo, Paulino Perez-Rodriguez, Jose Crossa.

Examples

## Not run: 

set.seed(123)
n <- 50
p <- 10
X <- matrix(rnorm(n * p), n, p)
y <- 1 + X[, 1] - 0.5 * X[, 2] + rnorm(n)
fitall <- HDBRR(y, X, intercept = TRUE, corpred = "eb", c = 100)
fitall
summary(fitall, crit = 0)
plot(fitall, crit = 0)
predict(fitall)


## End(Not run)

Durum Wheat X

Description

Is a matrix (338 x 7594) with A balanced, four-way multiparental cross population was developed from four elite durum wheat cultivars (Neodur, Claudio, Colosseo, and Rascon/Tarro) that were chosen as diverse contributors of different alleles of agronomic relevance.

Source

International Maize and Wheat Improvement Center (CIMMYT), Mexico.

Extract coefficients from an HDBRR model

Description

Extract coefficients from an HDBRR model

Usage

## S3 method for class 'HDBRR'
coef(object, all = FALSE, ...)

Arguments

object

An HDBRR object, typically created by HDBRR().

all

Logical; if TRUE, print all coefficients. Otherwise, at most the first 250 coefficients are printed.

...

Additional arguments passed to or from other methods.

matop

Description

Compute the SVD or QR decomposition of the matrix X.

Usage

matop(y = NULL, X, method = c("svd", "qr"), bigmat = TRUE)

Arguments

y

The data vector (numeric, n) NAs allowed. The default value is NULL, It is possible to compute the SVD or QR decomposition without y.

X

Design Matrix of dimension n x p.

method

Options for the posterior computation. Two methods, "qr" and "svd" decomposition. The default value for the method is SVD decomposition.

bigmat

Use of the bigstatsr package. The default value for bigmat is TRUE.

Details

Use the bigstartsr package when p >> n. Auxiliary in the HDBRR function.

Value

If the method used is svd then the list containing the following components:

y

The data vector (numeric, n) NAs allowed.

X

Design Matrix of dimension n x p.

D

A vector containing the singular values of X, of length min(n,p).

L

A matrix whose columns contain the left singular vectors of X,

R

A matrix whose columns contain the right singular vectors of X.

ev

A vector containing the square of D.

Ly

The cross-product between the matrix L and vector y.

n

Number of rows of X.

p

Number of columns of X.

If the method used is qr then the list containing the following components:

y

The data vector (numeric, n) NAs allowed.

X

Design Matrix of dimension n x p.

R

An upper triangular matrix of dimension n x p.

n

Number of rows of X.

p

Number of columns of X.

Author(s)

Sergio Perez-Elizalde, Blanca E. Monroy-Castillo, Paulino Perez-Rodriguez.

See Also

qr, svd

Examples

n <- 30
p <- 100
X <- matrix(rnorm(n*(p-1),1,1/p),nrow = n,ncol = p-1)
Beta <- sample(1:p,p-1,rep = FALSE)
Beta <- c(1,Beta)
y <- cbind(rep(1,n),X) %*% Beta+rnorm(n,0,1)
matop(y, X, bigmat = TRUE)

Durum Wheat

Description

The final number of SNPs included in the NCCR linkage map was 7594. The markers were centered and standardized. Phenotypic evaluation of the NCCR population was performed during two growing seasons (2010-2011 and 2011-2012) in locations in the Po Valley representative of the target environments where durum wheat is grown: Cadriano in the 2010-2011 growin season (Cad11) and the 2011-2012 growing season (Cad12); Poggio Renatico in the 2010-2011 growing season (Pr11) and Argelato in the 2011-2012 growing season (Arg12).

Source

International Maize and Wheat Improvement Center (CIMMYT), Mexico.

Durum wheat dataset

Description

This contain data from a multiparental durum wheat (Triticum turgidum L. spp. duram) trial consisting of 334 lines evaluated in a country-year combination. This population is characterized for Grain Yield (GY), grain volume weight (GVW), 1000-kernel weight (GWT) and heading date (HD) in the four environments. For further details see the vignettes in the package.

Usage

  data(phenowheat)

Format

pheno

Matrix phenowheat.pheno contains the phenotypic data.

X

The matrix phenowheat.X contains the genotypic data.

Plot an HDBRR model

Description

Plot an HDBRR model

Usage

## S3 method for class 'HDBRR'
plot(x, crit = log(4), var_select = FALSE, post = FALSE, ...)

Arguments

x

An HDBRR object, typically created by HDBRR().

crit

Numeric lower bound for the log Bayes factor used to select variables. Defaults to log(4).

var_select

Logical; if TRUE, also plot variable-selection results.

post

Logical; if TRUE, also plot the marginal posterior of u.

...

Additional arguments passed to or from other methods.

Predict from an HDBRR model

Description

Predict from an HDBRR model

Usage

## S3 method for class 'HDBRR'
predict(object, ...)

Arguments

object

An HDBRR object, typically created by HDBRR().

...

Additional arguments passed to or from other methods.

Print an HDBRR model

Description

Print an HDBRR model

Usage

## S3 method for class 'HDBRR'
print(x, ...)

## S3 method for class 'summary.HDBRR'
print(x, ...)

Arguments

x

An HDBRR object or a summary.HDBRR object.

...

Additional arguments passed to or from other methods.

Summarize an HDBRR model

Description

Summarize an HDBRR model

Usage

## S3 method for class 'HDBRR'
summary(object, all.coef = FALSE, crit = log(4), ...)

Arguments

object

An HDBRR object, typically created by HDBRR().

all.coef

Logical; should all coefficients be included? Defaults to FALSE.

crit

Numeric lower bound for the log Bayes factor used to select variables. Defaults to log(4).

...

Additional arguments passed to or from other methods.