GLSMeans: Generalized Least Squares
In jointMeanCov: Joint Mean and Covariance Estimation for Matrix-Variate Data

Description Usage Arguments Details Value

This function applies generalized least squares to estimate the unknown parameters of a linear model X = D beta + E, where X has dimension n by m, D has dimension n by k, and beta has dimension k by m.

1	GLSMeans(X, D, B.inv)

`X`	data matrix.
`D`	design matrix.
`B.inv`	inverse covariance matrix.

Example

X <- matrix(1:12, nrow=4, ncol=3)
D <- twoGroupDesignMatrix(1:2, 3:4)
B.inv <- diag(4)
beta.hat <- GLSMeans(X, D, B.inv)

Returns the estimated parameters of the linear model, a matrix of dimensions k by m, where k is the number of columns of D, and m is the number of columns of X.

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