plspm (version 0.5.1)

rebus.test: Permutation Test for REBUS Multi-Group Comparison

Description

Performs permutation tests for comparing pairs of groups from a REBUS object.

Usage

rebus.test(pls, reb, Y = NULL)

Value

An object of class "rebus.test", basically a list containing the results of each pair of compared classes. In turn, each element of the list is also a list with the results for the path coefficients, loadings, and GoF index.

Arguments

pls

Object of class "plspm" returned by plspm

reb

Object of class "rebus" returned by either rebus.pls or it.reb.

Y

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

Author

Laura Trinchera, Gaston Sanchez

Details

A permutation test on path coefficients, loadings, and GoF index is applied to the classes obtained from REBUS, by comparing two classes at a time. That is to say, a permutation test is applied on pair of classes. The number of permutations in each test is 100. In turn, the number of classes handled by rebus.test is limited to 6.

When pls$data=NULL (there is no data matrix), the user must provide the data matrix or data frame in Y.

References

Chin, W.W. (2003) A permutation procedure for multi-group comparison of PLS models. In: Vilares M., Tenenhaus M., Coelho P., Esposito Vinzi V., Morineau A. (Eds.) PLS and Related Methods - Proceedings of the International Symposium PLS03. Decisia, pp. 33-43.

See Also

rebus.pls, local.models

Examples

if (FALSE) {
 ## typical example of PLS-PM in customer satisfaction analysis
 ## model with six LVs and reflective indicators
 ## example of rebus analysis with simulated data

 # load data
 data(simdata)

 # Calculate plspm
 sim_path = matrix(c(0,0,0,0,0,0,1,1,0), 3, 3, byrow=TRUE)
 dimnames(sim_path) = list(c("Price", "Quality", "Satisfaction"),
                            c("Price", "Quality", "Satisfaction"))
 sim_blocks = list(c(1,2,3,4,5), c(6,7,8,9,10), c(11,12,13))
 sim_mod = c("A", "A", "A")  # reflective indicators
 sim_global = plspm(simdata, sim_path,
                    sim_blocks, modes=sim_mod)
 sim_global

 # Cluster analysis on residuals of global model
 sim_clus = res.clus(sim_global)

 # Iterative steps of REBUS algorithm on 2 classes
 rebus_sim = it.reb(sim_global, sim_clus, nk=2,
                    stop.crit=0.005, iter.max=100)

 # apply rebus.test
 sim_permu = rebus.test(sim_global, rebus_sim)

 # inspect sim.rebus
 sim_permu
 sim_permu$test_1_2

 # or equivalently
 sim_permu[[1]]
 }