Stat 243 Final Project
Switch branches/tags
Nothing to show
Clone or download
Pull request Compare This branch is even with fussballball:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
mfa
sandbox
slides
.gitignore
LICENSE.txt
README.md
mfa_0.1.tar.gz

README.md

Multiple Factor Analysis in R

Multiple factor analysis (MFA, also called multiple factorial analysis) is an extension of principal component analysis (PCA) tailored to handle multiple data tables that measure sets of variables collected on the same observations…

This description is from the paper that this project is based upon: Multiple factor analysis: principal component analysis for multitable and multiblock data sets by Hervé Abdi, Lynne J. Williams and Domininique Valentin (2013)

Contents

Quick Start Guide

# Install and load package through devtools
library(devtools)
devtools::install_github("fussballball/stat243FinalProject/mfa", 
                         force_deps = FALSE)
library(mfa)

# Fit an MFA model on the wines dataset
data(wine)                                    
i <- grep("V", colnames(wine))                
wine_ratings <- wine[,i]                              
expert_sets <- list(1:6, 7:12, 13:18, 19:23, 24:29,  
                    30:34, 35:38, 39:44, 45:49, 50:53)
wine_region <- substr(wine$ID, 1, 2)
wine_names <- as.character(wine$ID)
MFA <- mfa(data = wine_ratings, sets = expert_sets
          , color = wine_region, ids = wine_names)

# Get a summary of the MFA object
print(MFA)

# Print out the eigenvalue summary
summary_eigenvalues(MFA)

# Plot the compromise scores, partial factor scores, and variable loadings
plot(MFA)

Package Developers

  • Dario Cantore
  • Josiah Davis
  • Yanli Fan
  • Yoni Ackerman

References