multigroup.pls: PATHMOX-PLS: Extended Segmentation Trees in Partial Least Squares Structutal Equation Modeling (PLS-SEM)

Description

The function multigroup.pls performs a group comparison test for comparing path coefficients between two groups (classical multigroup approach for PLS-SEM). The null and alternative hypotheses to be tested are: H0: path coefficients are not significantly different; H1: path coefficients are significantly different

Usage

multigroup.pls(
  x,
  inner,
  outer,
  mode,
  scheme = "path",
  scaled = TRUE,
  cat,
  ng = 500,
  method = "parametric",
  ...
)

Arguments

matrix or data frame containing the manifest variables.

inner

A square (lower triangular) boolean matrix representing the inner model (i.e. the path relationships between latent variables).

outer

list of vectors with column indices or column names from x indicating the sets of manifest variables forming each block (i.e. which manifest variables correspond to each block).

mode

character vector indicating the type of measurement for each block. Possible values are: "A", "B", "newA", "PLScore", "PLScow". The length of mode must be equal to the length of outer.

scheme

string indicating the type of inner weighting scheme. Possible values are "centroid", "factorial", or "path".By default is "path".

scaled

whether manifest variables should be standardized. By the default (TRUE, scaled to standardized values (mean=0 and variance=1).

cat

the caterogical variable used for the comparison.

number of resamplig used to calculate the test

method

is the method used to test differences in path coefficients. There are two test availables: the parametric test and the permutation test By defalut is equal to parametric.

…

Further arguments passed on to multigroup.pls.

Value

Basically a list with the following results:

global_and_group_path_coeff

Path coefficients estimated for the global and the local models defined according to the level of teh categorical variable

abs_path_diff

absolute difference of the path coefficients estimated for the local models

multigroup_pvalue

LP-value test of comparison

Details

The argument x must be a data frame containing the manifest variables of the PLS-SEM model.

The argument cat must be the caterogical variable used for teh comparison.

ng number of resampling.

The argument method is a string contaning the criterion used to calculate the tests; if method="parametric" the classic parametric approach is used to perform the tests; if method="permutation" the Chin 2003 permutation testis used.

References

Hair, J. F. et al.(2018) Advanced issues in partial least squares structural equation modeling. Thousand Oaks: SAGE Publications (2018)