mda.start {mda}R Documentation

Provide starting weights for the mda function

Usage

mda.start(x, g, subclasses = 3, trace.mda.start = FALSE,
          start.method = c("kmeans", "lvq"), tries = 5,
          criterion = c("misclassification", "deviance"), ...)

Arguments

x The x data, or an mda object
g The response vector g
subclasses number of subclasses per class, as in mda.
trace.mda.start Show results of each iteration
start.method Either "kmeans" or "lvq". The latter requires the statlib contribution "classif".
tries Number of random starts
criterion By default, classification errors on the training data. Posterior deviance is also an option.

Value

A list of weight matrices, one for each class


[Package Contents]