rescale: Rescale Latent Variable Scores

In plspm: Partial Least Squares Path Modeling (PLS-PM)

Rescale Latent Variable Scores

Description

Rescale standardized latent variable scores to original scale of manifest variables

Usage

  rescale(pls, data = NULL)

Arguments

pls	object of class "plspm"
data	Optional dataset (matrix or data frame) used when argument dataset=NULL inside pls.

Details

rescale requires all outer weights to be positive

Value

A data frame with the rescaled latent variable scores

Author(s)

Gaston Sanchez

See Also

plspm

Examples

## Not run: 
 ## example with customer satisfaction analysis

 # load data satisfaction
 data(satisfaction)

 # define inner model matrix
 IMAG = c(0,0,0,0,0,0)
 EXPE = c(1,0,0,0,0,0)
 QUAL = c(0,1,0,0,0,0)
 VAL = c(0,1,1,0,0,0)
 SAT = c(1,1,1,1,0,0)
 LOY = c(1,0,0,0,1,0)
 sat_path = rbind(IMAG, EXPE, QUAL, VAL, SAT, LOY)

 # define outer model list
 sat_blocks = list(1:5, 6:10, 11:15, 16:19, 20:23, 24:27)

 # define vector of reflective modes
 sat_modes = rep("A", 6)

 # apply plspm
 my_pls = plspm(satisfaction, sat_path, sat_blocks, modes = sat_modes,
              scaled=FALSE)

 # rescaling standardized scores of latent variables
 new_scores = rescale(my_pls)

 # compare standardized LVs against rescaled LVs
 summary(my_pls$scores)
 summary(new_scores)
 
## End(Not run)

plspm documentation built on March 31, 2023, 11:54 p.m.