Treating visualization as a process

Posted to Statistics  |  Tags:  |  Nathan Yau

Many people think of visualization as a plug-in tool that spits out something to look at. Microsoft Excel comes to mind. Some think of visualization as just that final chart to put on a presentation slide. However, there’s always a backstory about how it was made, who made it, why it was made, and most importantly, how the data came about. This is often more important than the finished product.

Artist Jer Thorp wrote about this a while back — about how visualization is a process. More recently, Jake Porway, the director of DataKind, wrote more about the process and how it ties into more rigorous analyses.

When data visualization is used simply to show alluring infographics about whether people like Coke or Pepsi better, the stakes of persuasion like this are low. But when they are used as arguments for or against public policy, the misuse of data visualization to persuade can have drastic consequences. Data visualization without rigorous analysis is at best just rhetoric and, at worse, incredibly harmful.

You need that analysis to figure out what you actually see in a visualization.

For those who make data graphics, this means picking and prodding at the data before you throw up a graph. For example, mean and median can mean a lot of things for a distribution. For those on the consumption side, this means questioning each graphic you see and don’t take every at face value. The bars and lines are usually much more squishy than they appear on the screen.

Favorites

Where Bars Outnumber Grocery Stores

A closer look at the age old question of where there are more bars than grocery stores, and vice versa.

Famous Movie Quotes as Charts

In celebration of their 100-year anniversary, the American Film Institute selected the 100 most memorable quotes from American cinema, and …

Divorce Rates for Different Groups

We know when people usually get married. We know who never marries. Finally, it’s time to look at the other side: divorce and remarriage.

Life expectancy changes

The data goes back to 1960 and up to the most current estimates for 2009. Each line represents a country.