Choosing the right graph type to display your healthcare data is only part of the battle. You also need to keep an eye on details such as the scale of the graph’s axes. Software applications default to the maximum value being encoded, so you need to manually adjust those values to make sure they properly convey the meaning in your data.
Here is how a sample deviation graph looks when I let the software application automatically format the X-axis:
Although the bars encode the values correctly, the smaller scale on the left side makes the entire graph look skewed. It is difficult to fully and accurately evaluate the values being displayed.
Now look at this corrected version:
Since the ranges on the two sides of the deviation graph are now equal, the data view affords a clearer understanding of the information it presents, and eliminates the skewed effect of the first graph.
Yes, dear readers: scale matters!