pcbic.stepwise function

Choosing a good pattern

Uses the stepwise procedure described in Section 13.1.4 to find a pattern for a set of observed eigenvalues with good BIC value.

pcbic.stepwise(eigenvals, n)

Arguments

• eigenvals: The $Q$-vector of eigenvalues of the covariance matrix, in order from largest to smallest.
• n: The degrees of freedom in the covariance matrix.

Returns

A list with the following components:

• Patterns: A list of patterns, one for each value of length $K$.
• BICs: A vector of the BIC's for the above patterns.
• BestBIC: The best (smallest) value among the BIC's in BICs.
• BestPattern: The pattern with the best BIC.
• lambdaHat: A $Q$-vector containing the MLE's for the eigenvalues for the pattern with the best BIC.

Examples

# Build cars1
require("mclust")
mcars <- Mclust(cars)
cars1 <- cars[mcars$classification == 1, ]
xcars <- scale(cars1)
eg <- eigen(var(xcars))
pcbic.stepwise(eg$values, 95)

See Also

pcbic, pcbic.unite, and pcbic.subpatterns.