Annuaire
Christophe BONTEMPS, Toulouse School of Economics INRA
| Quand ? |
Le 10/01/2020, de 11:00 à 12:00 |
|---|---|
| S'adresser à | Salle des thèses, Equipe Gandrillon |
| Ajouter un événement au calendrier |
vCal
iCal
|
Data visualization is a fundamental ingredient of data science as is “forces us to notice what we never expected to see” (Tuckey,1977). Graphical methods have proved for a long time to be powerful tools both for data analysis, when one wants to visually explore a dataset, and for communicating data-based results. As such, data visualization is one of the most widely used tools of statistics, and probably the most popular one.
However, data visualization can create distorted views of the underlying data. Voluntarily, or involuntarily, many students, but also researchers, data analysts, data journalists, etc. make mistakes in their practice of data visualization. The result is that the visual tests performed for data analysis, when the analyst wants to study or question a dataset, can be wrong or misleading. The structure of the data, patterns and (ir)regularities, groups, trends, outliers… may be misunderstood, leading to serious errors in the understanding of the underlying phenomena. Even worse, when used as a tool for communication and, as such, as a visual language, some graphics may present spurious relationships, false proportions and misleading results. In this talk, we show through real-life examples and case studies, how to manipulate some of the principles and rules of data visualization in order to deliberately lie with graphics. Our goal here is not Machiavellian but pedagogical: by showing the power of some (bad) practices, we preach for better ones.
Contact : Olivier Gandrillon