« How to mess up a bar chart | Main | The war on infographics »



You do find the best bad charts.

It's reasonable to ask whether a chart is needed to report on four responses. But even if you decide that it's merited, is there an issue with expressing results as percentages? While 3/4 does equal 75%, it seems to me that percentages connote a level of statistical confidence (and thus generalizability) that is absent here. I'd be curious to hear what others think.

Also, a quibble: As I look at it, your redo still suggests that 50% of three managers answered "yes." I think the quantities in the legend don't match your assumptions.

The comments to this entry are closed.

Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Book Blog

Link to junkcharts

Graphics design by Amanda Lee

The Read

Keep in Touch

follow me on Twitter