Analysing Categorical Data in R - useR! 2011 Tutorial

Tutorial: Analysing Categorical Data in R

Marine Cadoret, Applied Mathematics Department, Agrocampus Ouest, France
Sébastien Lê, Applied Mathematics Department, Agrocampus Ouest, France

Abstract

In many applications, people are interested in the relationship between categorical variables. The aim of this tutorial is to propose an overview of both descriptive and inferential methods for categorical data.

Outline

Topics will include:

Introduction to categorical data via genomic, sensory and ecological data and their specific problems.
Describing, analysing, and visualizing one categorical variable: graphical outputs, confidence interval for a proportion.
Describing, analysing, and visualizing two categorical variables: contingency table, Correspondence Analysis, Chi-square test. Application to textual data and open ended questions.
Describing, analysing, and visualizing several categorical variables: from Correspondence Analysis to Multiple Correspondence Analysis. Application to the analysis of multiple choice questionnaires: introducing and visualizing external information in the analysis.
Getting a typology of individuals described by several categorical variables: automatic description of groups of individuals obtained from a Hierarchical Ascending Classification. Introduction to Logistic Regression and Logit Models for multinomial responses.
Introduction to Logistic Regression and Logit Models for multinomial responses.

Intended Audience

Teachers in data mining and data analysis, researchers in applied fields, statisticians whose topic of interest is multivariate analysis of categorical data.

Prerequisites

No prior knowledge is required.

References