Conceptually similar to PCA, correspondence analysis a method is designed for discovering associstions in categorical rather than continuous data. Discover the informative 2D-plots for efficient data mapping.
Upon completion of this module, participants will be able :
- To understand the context of use for correspondence analysis
- To understand what the underlying principle of the technique is
- To understand the limitations of the classical categorical data analysis approach
- To run simple and multiple correspondence analysis
- To interpret statistical software output
This module is intended for all scientific staff who collect several categorical data (survey, administrative records) and who wish to graphically summarising them and identify associations for the purpose of data reduction.
This workshop introduces the important concepts in statistics and data analysis. It assumes that participants have no previous knowledge of statistics or that they have not used it for a long time.
- Introduction: Historical Note, Context of Use, Objective, Terminology
- Classical Analysis of Categorical Data with the Chi-Square Test & Limitations
- Simple Correspondence Analysis (SCA): Principle & Interpretation
- Multiple Correspondence Analysis (MCA) : Principle & Interpretation
- Implementation in Software Packages
Recommended Duration: Approximately 1 day
Course materials :