Tools for Partial Least Squares Path Modeling (PLS-PM)

Partial Least Squares Path Modeling (PLS-PM) analysis for both metric and non-metric data, as well as REBUS analysis.


News

  • re-submission addressing package's Description change requested by Kurt Hornick
  • changed package URL in DESCRIPTION
  • addes BugReports in DESCRIPTION
  • updated call to plot diagrams: diagram::plotmat
  • updated vignette with all plots displayed
  • fixed bug in rebus.pls example documentation
  • updated documentation in funciton plspm for non-metric argument scaling
  • updated install_github call in README
  • fixed bug in 'get_boots' so now repeated names of MVs in constructs of 2nd order are displayed when requiring bootstrapping
  • change package dependencies and Import options, in order to comply with CRAN Policies
  • fixed factorial scheme bug in get_weights_nonmetric
  • get_dummy allows x to include zero
  • fixing a bug for non-metric data in get_boots

NEW FEATURES

  • Full redesigning of the popular plspm package that now provides all the cool features for handling non-metric data.

  • argument maxiter replaces iter

  • new argument scaling to handle non-metric variables

  • term path_matrix replaces inner_matrix

  • term blocks replaces outer_list. Moreover, now you can specify blocks using character strings

  • inner_model gives the full set of coefficients results from 'lm'

  • Simplified output of plspm() containing data frames compatible with ggplot2

  • fixing a typo in print.plspm (thanks to Jeff Daniels)

  • Decreasing required R version to 2.14.0 (suggested by Mikko Ronkko)

  • innerplot allows parameter arr.lwd to be expressed as a matrix; this can be used to plot arrows with different line widths

  • fixing a typo in innerplot.Rd

  • fixing a typo in outerplot.Rd

  • changing print format of print.local.models

  • fixing a typo in futbol.Rd

  • new function rescale to express latent variable scores in scale of indicators

  • print.summary.plspm shows Model Specifications in an aligned (pretty) way

  • new data set offense for Offense Performance model (NFL teams 2011)

  • new data set college for GPA model (life sciences undergrad students)

  • new data set cereals for Cereals Rating model (cereals)

  • internal get_boots changed to 95% confidence interval

  • new data set technology for User and Acceptance of Technology model

NEW FEATURES AND FUNCTIONS

  • PLSTROIKA has started (restructuring my pls packages)

  • Revamped version of the renowned plspm package that from now on will only contain functions related to Partial Least Squares Path Modeling. Other methods such as nipasl, pls regression, and canonical analysis, now happily live in the package "plsdepot"

  • plspm has updated documentation

  • New implemented functions innerplot and outerplot to provide simpler but prettier graphics

  • delete split option for plotting loadings and outer weights

  • plot.plspm.groups has been deleted

  • resclus.plot has been deleted

  • internal functions are exported for developing reasons. Don't use them unless you're me or a super user or a package developer

  • Using 'roxygen2' for documentation and literate programming

BUG FIXES

  • Pain-in-the-butt warning message about 'sd() deprecated' has been tackled

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("plspm")

0.4.9 by ORPHANED, 3 months ago


https://github.com/gastonstat/plspm


Report a bug at https://github.com/gastonstat/plspm/issues


Browse source code at https://github.com/cran/plspm


Authors: Gaston Sanchez [aut, cre], Laura Trinchera [aut], Giorgio Russolillo [aut]


Documentation:   PDF Manual  


Task views: Chemometrics and Computational Physics, Psychometric Models and Methods


GPL-3 license


Imports tester, turner, diagram, shape, amap

Suggests plsdepot, FactoMineR, ggplot2, reshape, testthat, knitr


Imported by plspm.formula.

Depended on by genpathmox, pathmox.

Suggested by matrixpls, plsdepot.


See at CRAN