pathmox (version 0.2.0)

techmox: TECHMOX Algorithm: Segmentation Trees in PLS Path Modeling

Description

The function techmox calculates a binary segmentation tree following the TECHMOX algorithm. In contrast, fix.techmox obtains a supervised TECHMOX tree in the sense of allowing the user to interactively fix the partitions along the construction process of the tree.

Usage

techmox(pls, EXEV, X = NULL, signif = 0.05, size = 0.1, deep = 2, tree = TRUE)

Arguments

pls

An object of class "plspm" returned by plspm.

EXEV

A data frame of factors contaning the segmentation variables.

X

Optional dataset (matrix or data frame) used when argument dataset=NULL inside pls.

signif

A numeric value indicating the significance threshold of the F-statistic. Must be a decimal number between 0 and 1.

size

A numeric value indicating the minimum size of elements inside a node.

deep

An integer indicating the depth level of the tree. Must be an integer greater than 1.

tree

A logical value indicating if the tree should be displayed (TRUE by default).

Value

An object of class "treemox". Basically a list with the following results:

MOX

Data frame containing the results of the segmentation tree.

FT

Data frame containing the results of the F-tests for each node partition.

candidates

List of data frames containing the candidate splits of each node partition.

list.nodes

List of elements for each node.

Details

The argument EXEV must be a data frame containing segmentation variables as factors (see factor). The number of rows in EXEV must be the same as the number of rows in the data used in pls.

The argument size can be defined as a decimal value (i.e. proportion of elements inside a node), or as an integer (i.e. number of elements inside a node).

When the object pls does not contain a data matrix (i.e. pls$data=NULL), the user must provide the data matrix or data frame in X.

References

Sanchez, G. (2009) PATHMOX Approach: Segmentation Trees in Partial Least Squares Path Modeling. Doctoral Dissertation.

http://www.gastonsanchez.com/Pathmox_Approach_Thesis_Gaston_Sanchez.pdf

See Also

pathmox, plot.treemox treemox.pls.

Examples

## Not run: 
#  ## example of PLS-PM in customer satisfaction analysis
#  ## model with seven LVs and reflective indicators
#  data(csimobile)
# 
#  # select manifest variables
#  data_mobile = csimobile[,8:33]
# 
#  # define path matrix (inner model)
#  IMAG = c(0, 0, 0, 0, 0, 0, 0)
#  EXPE = c(1, 0, 0, 0, 0, 0, 0)
#  QUAL = c(0, 1, 0, 0, 0, 0, 0)
#  VAL = c(0, 1, 1, 0, 0, 0, 0)
#  SAT = c(1, 1, 1, 1, 0, 0, 0)
#  COM = c(0, 0, 0, 0, 1, 0, 0)
#  LOY = c(1, 0, 0, 0, 1, 1, 0)
#  mob_path = rbind(IMAG, EXPE, QUAL, VAL, SAT, COM, LOY)
# 
#  # blocks of indicators (outer model)
#  mob_blocks = list(1:5, 6:9, 10:15, 16:18, 19:21, 22:24, 25:26)
#  mob_modes = rep("A", 7)
# 
#  # apply plspm
#  mob_pls = plspm(data_mobile, mob_path, mob_blocks, modes = mob_modes,
#                  scheme = "factor", scaled = FALSE)
# 
#  # re-ordering those segmentation variables with ordinal scale
#  # (Age and Education)
#  csimobile$Education = factor(csimobile$Education,
#      levels=c("basic","highschool","university"),
#      ordered=TRUE)
# 
#  # select the segmentation variables
#  seg_vars = csimobile[,1:7]
# 
#  # Techmox Analysis
#  mob_techmox = techmox(mob_pls, seg_vars, signif=.10, size=.10, deep=2)
#  ## End(Not run)