GeminiB: Estimate Row-Row Covariance Structure Using Gemini

In jointMeanCov: Joint Mean and Covariance Estimation for Matrix-Variate Data

Description

GeminiB estimates the row-row covariance, inverse covariance, correlation, and inverse correlation matrices using Gemini. For identifiability, the covariance factors A and B are scaled so that A has trace m, where m is the number of columns of X, A is the column-column covariance matrix, and B is the row-row covariance matrix.

Usage

GeminiB(X, rowpen, penalize.diagonal = FALSE)

Arguments

X	Data matrix, of dimensions n by m.
rowpen	Glasso penalty parameter.
penalize.diagonal	Logical value indicating whether to penalize the off-diagonal entries of the correlation matrix. Default is FALSE.

Value

corr.B.hat	estimated correlation matrix.
corr.B.hat.inv	estimated inverse correlation matrix.
B.hat	estimated covariance matrix.
B.hat.inv	estimated inverse covariance matrix.

Examples

n1 <- 5
n2 <- 5
n <- n1 + n2
m <- 20
X <- matrix(rnorm(n * m), nrow=n, ncol=m)
rowpen <- sqrt(log(m) / n)
out <- GeminiB(X, rowpen, penalize.diagonal=FALSE)
# Display the estimated correlation matrix rounded to two
# decimal places.
print(round(out$corr.B.hat, 2))

jointMeanCov documentation built on May 6, 2019, 1:09 a.m.