varimp

plot.semforest.varimp

varimpConvergencePlot

print.semforest.varimp

A <code><a rd-options="" href="/link/semforest?package=semtree&version=0.9.12" data-mini-rdoc="semtree::semforest">semforest</a></code> object

forest

Covariates used in the forest creation process. NULL value will be automatically filled in by the function.

var.names

Boolean to print messages while function is running.

verbose

Experimental. Some alternative methods to compute importance. Default is "permutation".

method

Default is <code><a rd-options="" href="/link/evaluateTree?package=semtree&version=0.9.12" data-mini-rdoc="semtree::evaluateTree">evaluateTree</a></code> function. The value of the -2LL of the leaf nodes is compared to baseline overall model.

eval.fun

An object of class "cluster" representing a parallel socket cluster. See package <a rd-options="parallel" href="/link/makeCluster?package=semtree&version=0.9.12&to=parallel" data-mini-rdoc="parallel::makeCluster">makeCluster</a>.

cluster

&#8230;

A function to calculate relative variable importance for selecting node splits over 
a <code><a rd-options="" href="/link/semforest?package=semtree&version=0.9.12" data-mini-rdoc="semtree::semforest">semforest</a></code> object.

 ~kwd1 

 ~kwd2 

SEM Trees and SEM Forests -- an extension of model-based decision
trees and forests to Structural Equation Models (SEM). SEM trees hierarchically
split empirical data into homogeneous groups sharing similar data patterns
with respect to a SEM by recursively selecting optimal predictors of these
differences. SEM forests are an extension of SEM trees. They are ensembles of
SEM trees each built on a random sample of the original data. By aggregating
over a forest, we obtain measures of variable importance that are more robust
than measures from single trees.

Andreas M. Brandmaier andy@brandmaier.de

semtree

Recursive Partitioning for Structural Equation Models

Andreas M. Brandmaier 

John J. Prindle 

varimp function

A <code><a rd-options='' href='semforest'>semforest</a></code> object

Default is <code><a rd-options='' href='evaluateTree'>evaluateTree</a></code> function. The value of the -2LL of the leaf nodes is compared to baseline overall model.

An object of class "cluster" representing a parallel socket cluster. See package <a rd-options='parallel' href='makeCluster'>makeCluster</a>.

A function to calculate relative variable importance for selecting node splits over 
a <code><a rd-options='' href='semforest'>semforest</a></code> object.

varimp: SEM Forest Variable Importance

Description

Usage

Arguments

References