em.cov {EMgaussian}

EM algorithm for multivariate normal, covariance matrix parameterization

Description

EM algorithm for multivariate normal, covariance matrix parameterization

Usage

em.cov(
  dat,
  max.iter = 500,
  tol = 1e-05,
  start = c("diag", "pairwise", "listwise", "full"),
  debug = 0,
  ...
)

Arguments

dat

Data frame or matrix that contains the raw data.

max.iter

Max number of EM cycles.

tol

Tolerance for change in parameter estimates across EM Cycles. If all changes are less than tol, the algorithm terminates.

start

Starting value method (see details).

debug

(Experimental) set an integer value > 1 for some information as the algorithm runs.

...

Space for additional arguments, not currently used.

Details

This function computes all means and covariances among a set of variables using the Expectation-Maximization (EM) algorithm to handle missing values, and assuming multivariate normality. The EM code was originally developed for the precision matrix parameterization (em.prec), i.e., the parameters are the means and the inverse of the covariance matrix. But, this is easily modifiable to handle a covariance matrix parameterization such that means and covariances are the model parameters.

For starting values, the function accepts either a list that has mu and S slots corresponding to the starting mean and covariance matrix. This is useful if the user would like to use custom starting values. Otherwise, a character corresponding to any of the options available in the startvals.cov function will be used to take a guess at starting values.

Value

A list with the following:

• p.est: all parameter estimates as a vector (means followed by unique elements of precision matrix).

• mu: estimated means.

• S: estimated covariance matrix.

• it: number of EM cycles completed.

• conv: boolean value indicating convergence (TRUE) or not (FALSE).

Examples

  library(psych)
  data(bfi)
  test <- em.cov(bfi[,1:25])