Principal component methods are used to summarize and visualize the information contained in a large multivariate data sets. Here, we provide practical examples and course videos to compute and interpret principal component methods (PCA, CA, MCA, MFA, etc) using R software.
The following figure illustrates the type of analysis to be performed depending on the type of variables contained in the data set.
The Book:
Practical Guide to Principal Component Methods in R
Practical guide: R code and interpretation
We’ll mainly use two R packages:
FactoMineR: for computing principal component methods;factoextra: for extracting, visualizing and interpreting the results.
This section is organized as follow:
- BASICS
- Introduction to R
- R packages for principal component methods
- CLASSICAL METHODS
- PCA - Principal Component Analysis, for analyzing a data set containing continuous variables
- CA - Correspondence Analysis, for analyzing the association between two categorical variables.
- MCA - Multiple Correspondence Analysis, for analyzing a data set containing more than 2 categorical variables.
- ADVANCED METHODS
- FAMD - Factor Analysis of Mixed Data, for analyzing a data set containing both quantitative and qualitative variables.
- MFA - Multiple Factor Analysis, for analyzing a data set containing variables structured into groups.
- CLUSTERING
HCPC - Hierarchical Clustering on Principal Components
More examples
- Principal Component Analysis in R: prcomp vs princomp
- PCA in R Using Ade4: Quick Scripts
- Correspondence Analysis in R: Million Ways
- Correspondence Analysis: Theory and Practice
Course videos
- PCA in R Using FactoMineR: Quick Scripts and Videos
- CA in R Using FactoMineR: Quick Scripts and Videos
- MCA in R Using FactoMineR: Quick Scripts and Videos
- FAMD in R Using FactoMineR: Quick Scripts and Videos
- MFA in R Using FactoMineR: Quick Scripts and Videos
- HCPC Using FactoMineR: Videos
See also
Multidimensional Scaling Essentials: Algorithms and R Code
Required R Packages for Principal Component Methods
Bykassambara, The in Principal Component Methods in R: Practical Guide
FactoMineR & factoextraThere are a number of R packages implementing principal component methods. These packages include: FactoMineR, ade4, stats, ca, MASS and ExPosition.However, the result... [Read more]
Multidimensional Scaling Essentials: Algorithms and R Code
Bykassambara, The in Principal Component Methods in R: Practical Guide
Multidimensional scaling (MDS) is a multivariate data analysis approach that is used to visualize the similarity/dissimilarity between samples by plotting points in two dimensional... [Read more]
Correspondence Analysis in R: Million Ways
Bykassambara, The in Principal Component Methods in R: Practical Guide
This article describes the multiple ways to compute correspondence analysis in R (CA). Recall that, correspondence analysis is used to study the association between two categorical variables by... [Read more]
Correspondence Analysis: Theory and Practice
Bykassambara, The in Principal Component Methods in R: Practical Guide
This article presents the theory and the mathematical procedures behind correspondence Analysis. We write all the formula in a very simple format so that beginners can understand the... [Read more]
PCA in R Using Ade4: Quick Scripts
Bykassambara, The in Principal Component Methods in R: Practical Guide
This article provides quick start R codes to compute principal component analysis (PCA) using the function dudi.pca() in the ade4 R package. We’ll use the factoextra R package to visualize the... [Read more]
Principal Component Analysis in R: prcomp vs princomp
Bykassambara, The in Principal Component Methods in R: Practical Guide
This R tutorial describes how to perform a Principal Component Analysis (PCA) using the built-in R functions prcomp() and princomp(). You will learn how to predict new individuals and variables... [Read more]
HCPC - Hierarchical Clustering on Principal Components: Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
Clustering is one of the important data mining methods for discovering knowledge in multivariate data sets. The goal is to identify groups (i.e.clusters) of similar objects within a data... [Read more]
MFA - Multiple Factor Analysis in R: Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
Multiple factor analysis (MFA) (J. Pagès 2002) is a multivariate data analysis method for summarizing and visualizing a complex data table in which individuals are described by several sets... [Read more]
FAMD - Factor Analysis of Mixed Data in R: Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
Factor analysis of mixed data (FAMD) is a principal component method dedicated to analyze a data set containing both quantitative and qualitative variables (Pagès 2004). It makes it possible... [Read more]
MCA - Multiple Correspondence Analysis in R: Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
The Multiple correspondence analysis (MCA) is an extension of the simple correspondence analysis (chapter @ref(correspondence-analysis)) for summarizing and visualizing a data table containing... [Read more]
CA - Correspondence Analysis in R: Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
Correspondence analysis (CA) is an extension of principal component analysis (Chapter @ref(principal-component-analysis)) suited to explore relationships among qualitative variables (or... [Read more]
PCA - Principal Component Analysis Essentials
Bykassambara, The in Principal Component Methods in R: Practical Guide
Principal component analysis (PCA) allows us to summarize and to visualize the information in a data set containing individuals/observations described by multiple inter-correlated quantitative... [Read more]
