Profile Analysis of Multivariate Data in R

A suite of multivariate methods and data visualization tools to implement profile analysis and cross-validation techniques described in Davison & Davenport (2002) , Bulut (2013) < http://conservancy.umn.edu/handle/11299/155592>, and other published and unpublished resources. The package includes routines to perform criterion-related profile analysis, profile analysis via multidimensional scaling, moderated profile analysis, profile analysis by group, and a within-person factor model to derive score profiles.


###Title: Profile Analysis of Multivariate Data in R

###Type: Package

Development version: v0.3-3 on GitHub

Description: Fit profile analytic models. This includes the multivariate methods and data visualization tools to implement profile analysis and cross-validation techniques described in Davison & Davenport (2002) and Bulut (2013).

Released versions are installable from CRAN and the developmental version can be installed by:

devtools::install_github(repo = "cddesja/profileR", build_vignettes = TRUE)

The build_vignettes = TRUE argument can be omitted if you do not want to build the vignette (or the build is causing problems). To view the vignette for the profileR package:

library("profileR")
vignette("jss_profileR")
  • Added JSS unpublished, and under review, manuscript as a vignette.
  • Added the spouse data in the package.
  • Added wprifm, which performs a within-person random intercept factor model to obtain a score profile.
  • EXPERIMENTAL: Added moderated profile analysis. This function is untested and best on unpublished methodology.
  • Changed cp to cpa to avoid confusion with cp in Linux and Mac environments.
  • Changed pc to pcv.

News

Changes in version: profileR_0.3-3

  • the pbg function can now analyze profiles cross two or more groups. Also, the terminology in the function has been revised.

  • Now, the pams and pbg functions define the data as "data" rather than x in the functions.

  • A few minor typos haven corrected in the help files.

Changes in version: profileR_0.3-1

  • Added the "spouse" data as a part of the package. Now the pbg function can be directly examined using the spouse data.

  • Added unpublished Journal of Statistical Software manuscript as a vignette.

Changes in version: profileR_0.3

  • Changed cp to cpa and pc to pcv.

  • Added wprifm, which performs a within-person random intercept factor model to obtain a score profile.

  • EXPERIMENTAL: Added moderated profile analysis. This function is untested and best on unpublished methodology.

Changes in version: profileR_0.2-1

  • Standardize option was added to profileplot. This allows users to center all scores before plotting them using the profileplot function.

  • Fixed the legend issue on profileplot function when by.pattern is set to FALSE.

  • Fixed cp and pc functions. They weren't working with missing data because of default na.action. This is fine now.

  • Fixed typos in manpages.

  • Fixed plot for critpat class.

Changes in version: profileR_0.2

  • Added pams(). This function adds profile analysis via multidimensional scaling.

  • Add pbg(). This function tests parallel, level, and coincidential profiles across two groups.

  • Add additional generic functions to classes critpat, prof, and profg.

  • Renamed functions to reduce conflict with base functions and to introduce a coding convention.

Changes in version: profileR_0.1

  • Initial CRAN release

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("profileR")

0.3-4 by Christopher David Desjardins, 7 months ago


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


Authors: Okan Bulut <okanbulut84@gmail.com>, Christopher David Desjardins <cddesjardins@gmail.com>


Documentation:   PDF Manual  


Task views: Psychometric Models and Methods


GPL (>= 2) license


Depends on ggplot2, RColorBrewer, reshape, lavaan


See at CRAN