Dimensionality Reduction Techniques for Multivariate Categorical Data
- 13 June 2025
- book chapter
- Published by IGI Global Scientific Publishing
- p. 1-36
Abstract
High-dimensional categorical data challenges Data Science, Machine Learning, and Statistics in analyzing variability and interpretation. Using the “Forest Cover Type” dataset (n=581,012), this paper explores dimensionality reduction methods: PCA, MCA, CATPCA, FAMD, MFA, and NLCCA. Results show no method is universally best; the choice depends on data and goals. Advanced strategies like combining PCA, MCA, and CATPCA offer unique insights, emphasizing diverse approaches tailored to study objectives.Keywords
This publication has 37 references indexed in Scilit:
- Robustness of Principal Component Analysis with Spearman’s Rank MatrixJournal of Statistical Theory and Practice, 2024
- Multivariate data analysis of categorical data: taking advantage of the rhetorical power of numbers in qualitative researchQuality & Quantity, 2023
- Extracting activity patterns: Exploratory data analysis on a fucoidan extract data set with mixed variablesAlgal Research, 2021
- Categorical Data Analysis by Example2016
- Multiple correspondence analysis: one only or several techniques?Quality & Quantity, 2015
- Multiple factor analysis: principal component analysis for multitable and multiblock data setsWIREs Computational Statistics, 2013
- Visualization of Categorical Data1998
- OVERALSComputational Statistics & Data Analysis, 1994
- Interpreting multiple correspondence analysisApplied Stochastic Models and Data Analysis, 1991
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991