« The Numbers Guy went on vacation | Main | How effective visualization brings data alive »



The use of lines in dot plots conventionally marks a break in the data, such as when there's a gap in the measurements or when 2 different series which are not totally comparable are plotted together. I thought that was the case here.


The question needs to be asked whether it would be better to superpose the graphs.


Yes I was going to say something along the lines of what Domingo has already said (though I wasn't aware of any convention about lines in dot plots). These lines seem to indicate survey breaks rather than big changes as such.


Domingo/Sumit: I haven't thought about the use of lines to indicate survey breaks. My interpretation of large shifts doesn't work for one or two of those charts.

I don't like the idea though - it requires that "knowledge in the head", knowing the convention; and it draws attention to the holes in the data set, rather than the data in the data set.

Ken: hard to tell unless we actually plot the superposed version.

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