Data Analysis and Visualization

Data visualisation requires us to draw upon a network of persuasive modes and media we use to communicate with readers. Technical communicators use written language to label and describe data, visual and graphic representation to show data, and spacial and mathematical reasoning to illuminate the “story” of the data. 

Four principles of good data visualization, according to Edward Tufte:

  1. Placing the data in an appropriate context for cause and effect.
  2. Making quantitative comparisons.
  3. Considering alternative explanations and contrary cases.
  4. Assessment of possible errors in the numbers reported in graphics.

“There are right ways and wrong ways to show data; there are displays that reveal the truth and displays that do not.”

Data Analysis Practice

To practice analyzing data, choose a link below and answer the following questions.

  1. What is the story being told with this data? What comparisons are being made, and/or what aspects of the data are highlighted? 
  2. What other stories could be told about this data, and how would we change the dataset or the type of visualization to tell that story? 
  3. What else might you want to know about this dataset? What information is not here? 

Eight Core Principles of Data Visualization

According to Stephen Few.

  1. Simplify – Just like an artist can capture the essence of an emotion with just a few lines, good data visualization captures the essence of data – without oversimplifying.
  2. Compare – We need to be able to compare our data visualizations side by side. We can’t hold the details of our data visualizations in our memory – shift the burden of effort to our eyes.
  3. Attend – The tool needs to make it easy for us to attend to the data that’s really important. Our brains are easily encouraged to pay attention to the relevant or irrelevant details. 
  4. Explore – Data visualization tools should let us just look. Not just to answer a specific question, but to explore data and discover things. Directed and exploratory analysis are equally valid, but we need to be sure that out visualization tool makes both possible.
  5. View Diversely – Different views of the same data provide different insights. It helps to be able to look at the same data from different perspectives at the same time and see how they fit together.
  6. Ask why – More than knowing “what’s happening”, we need to know “why it’s happening”. This is where actionable results come from.
  7. Be skeptical – We too rarely question the answers we get from our data because traditional tools have made data analysis so hard. We accept the first answer we get simply because exploring any further is tool hard. 
  8. Respond – Simply answering questions for yourself has limited benefit. It’s the ability to share our data that leads to global enlightenment.