Description:

[Video 5 begin]
When creating your own visualizations, you can begin planning out your visualization using the ASK acronym. First, consider the accuracy of the data you want to visualize by understanding the difference between correlation and causation, and by understanding the role bias can play in data collection
If you know your data well you will be able to spot mistakes. Keep in mind that viewers with an inquisitive nature or investigative curiosity about data may also be able to spot mistakes. Take the time to get to know your data so you can be confident and comfortable with the story you are telling!

In addition to identifying intention and spotting mistakes, be alert to the difference between correlation and causation between data points. Data points can correlate by happening at the same time or in the same location, but this correlation doesn’t necessarily mean one caused or influenced the other. [image: http://news.bbc.co.uk/2/hi/health/3086013.stm] For example,The BBC reported that an Italian study finds that eating pizza cuts cancer risks. But did the study find enough data to support this conclusion? The researchers interviewed 3,300 people who had developed cancers, and 5,000 people who were cancer free, and found that “Those who ate pizza at least once a week had less chance of developing cancer.” But perhaps there are a few things missing here? Like, what were the exercise and smoking habits, or other detailed lifestyle choices of the participants. Did they survey a population greater than those regularly exposed to pizzerias in their vicinity? So you see, the data can tell you something, and a headline can be established but be aware of potential manipulation by misconstruing the accuracy of data. [use call-outs in Camtasia to highlight and circle and question some statements in this article]. While the lunacy of this example is not an official medical study, some misrepresentations of data are not as obvious. Just be mindful that data, although facts about something that occurred to a population, must always be analyzed by others critically for miscalculations, misinterpretations, and misconstructions.
[video 5 end]