mimi (version 0.1.0)

mimi.lr: mimi.lr Compute solution of mimi for low-rank model along regularization path

Description

mimi.lr Compute solution of mimi for low-rank model along regularization path

Usage

mimi.lr(y, var.type = c("gaussian", "binary", "poisson"), lambda1,
  maxit = 100, theta0 = NULL, thresh = 1e-05, trace.it = F,
  max.rank = NULL)

Arguments

y

nxp observation matrix

var.type

vector of length p indicating types of y columns (gaussian, binary, poisson)

lambda1

positive number, regularization parameter for nuclear norm penalty

maxit

integer, maximum number of iterations

theta0

matrix of size nxp, initial interactions (optional)

thresh

positive number, convergence criterion

trace.it

boolean, whether convergence information should be printed

max.rank

integer, maximum rank of interaction matrix

Value

A list with the following elements

yimputed

the imputed data set

theta

estimated low-rank matrix

Examples

# NOT RUN {
y0 <- matrix(rnorm(6 * 10), nrow = 6)
y0[sample(1:50, size = 10)] <- NA
var.type <- rep("gaussian", 10)
res <- mimi.lr(y0, var.type, lambda1 = 0.1)
# }