# Blog.

## Correspondence Analysis.

This is the ultimate guide for correspondence analysis, visualization, and interpretation. Everything you need to know is here: from basic how tos to tips and tricks that will aid in interpretation to advanced concepts. Worked examples are shown in Displayr, R and Q.

Correspondence analysis is a popular data science technique. It turns large tables of data into relatively easy to read visualizations. Which makes it easier to find key insights in the data. Correspondence analysis is also commonly used by market researchers to create brand switching and positioning maps. Scatter plots are the most common way to visualize results. However, moon plots have the same conclusions, are often even easier to interpret.

Adding Supplementary Points to a Correspondence Analysis
17 August 2017 | by Jake Hoare

Retrospectively adding supplementary points to a correspondence analysis can greatly assist in the interpretation of results. In other words, including supplementary row or column points to a correspondence analysis after the core data has determined…

Moonplots: A Better Visualization for Brand Maps
15 August 2017 | by Tim Bock

Moonplots are a better way to visualize brand maps than standard correspondence analysis outputs, which are often difficult to read correctly. The Moonplot resolves the key interpretation issues of correspondence analysis and is usually a…

Normalization and Scaling in Correspondence Analysis
08 August 2017 | by Tim Bock

This post gives recommendations for the best approach to normalization for different situations, making correspondence plots less misleading.

Understanding the Math of Correspondence Analysis
08 August 2017 | by Tim Bock

If you’ve ever wanted a deeper understanding of what’s going on behind the scenes of correspondence analysis, then this post is for you. Correspondence analysis is a popular tool for visualizing the patterns in large…

Correspondence Analysis of Square Tables
25 July 2017 | by Jake Hoare

Square tables are data tables where the rows and columns have the same labels, commonly seen as a crosstab of brand switching or brand repertoire data. Correspondence analysis is often used to visualize these tables as…

Customization of Bubble Charts for Correspondence Analysis in Displayr
08 July 2017 | by Tim Bock

When you insert a bubble chart in Displayr (Insert > Visualization > Labeled Bubbleplot), you can customize some aspects of its appearance from the controls that appear in the object inspector on the right of the screen. More advanced customizations…

Customization of Bubble Charts for Correspondence Analysis in Q
08 July 2017 | by Tim Bock

When you insert a bubble chart in Q (Create > Charts > Visualization > Labeled Bubbleplot), you can customize some aspects of its appearance from the controls that appear in the object inspector on the right of the…

Using Bubble Charts to Show Significant Relationships and Residuals in Correspondence Analysis
08 July 2017 | by Tim Bock

While correspondence analysis does a great job at highlighting relationships in large tables, a practical problem is that correspondence analysis only shows the strongest relationships, and sometimes some of the weaker relationships may be of more interest. One…

When to Use, and Not Use, Correspondence Analysis
23 May 2017 | by Tim Bock

Correspondence analysis is one of those rare data science tools which make things simpler. You start with a big table that is too hard to read, and end with a relatively simple visualization. In this…

Using Correspondence Analysis to Compare Sub-Groups and Understand Trends
22 May 2017 | by Tim Bock

This post shows how to use correspondence analysis to compare sub-groups. It focuses on one of the most interesting types of sub-groups: data at different points in time. This is variously known as trend, tracking, longitudinal and time series data. The end-goal…

Correspondence Analysis Versus Multiple Correspondence Analysis: Which to Use and When?
22 May 2017 | by Tim Bock

Let me cut to the chase. Multiple correspondence analysis sounds better than correspondence analysis. But, for 99% of real-world data problems, correspondence analysis is the more useful technique. In this post I explain the difference…