RPMM (version 1.20)

glcSplitCriterionJustRecordEverything: Gaussian RPMM Split Criterion: Always Split and Record Everything

Description

Split criterion function: always split, but record everything as you go.

Usage

glcSplitCriterionJustRecordEverything(llike1, llike2, weight, ww, J, level)

Arguments

llike1
one-class likelihood.
llike2
two-class likelihood.
weight
weights from RPMM node.
ww
“ww” from RPMM node.
J
Number of items.
level
Node level.

Value

llike1
Just returns llike1
llike2
Just returns llike2
J
Just returns J
weight
Just returns weight
ww
Just returns ww
degFreedom
Degrees-of-freedom for LRT
chiSquareStat
Chi-square statistic
split
TRUE=split the node, FALSE=do not split the node.

Details

This is a function of the form “glcSplitCriterion...”, which is required to return a list with at least a boolean value split, along with supporting information. This function ALWAYS returns split=TRUE. Useful for gathering information. It is recommended that you set the maxlev argument in the main function to something less than infinity (say, 3 or 4). See glcTree for example of using “glcSplitCriterion...” to control split.

See Also

glcSplitCriterionBIC, glcSplitCriterionBICICL, glcSplitCriterionLevelWtdBIC, glcSplitCriterionLRT