Note: Images may be inserted into your messages by uploading a file attachment (see "Manage Attachments"). Even though it doesn't appear when previewed, the image will appear at the end of your message once it is posted.
Register Latest Topics

  Author   Comment  

Posts: 99
Reply with quote  #1 

For the April/May/June 2017 Visual Business Intelligence Newsletter article, titled The DataVis Jitterbug: Let’s Improve an Old Dance, Stephen discusses the problem of "over-plotting," which is when some data-encoding objects, such as dots in a scatterplot, cover other data objects, hiding them. "Jittering" has long been a potential solution to this problem, but it comes with its own issues and is especially problematic in strip plots. In the article, Stephen suggests best practices for jittering in scatterplots and introduces a new kind of jittered graph, which he calls a "wheat plot," as an improved way of jittering values that overlap in a strip plot.

What are your thoughts about the article? We invite you to post your comments here.



Posts: 823
Reply with quote  #2 
I was reminded via email a few minutes ago that Daniel Zvinca, who participates frequently in this discussion forum, introduced a design that is almost exactly what I'm calling a "wheat plot." I don't recall ever reading Dan's idea, but I'm sure that I must have when he originally posted it back in 2014. The fact that two people with a great deal of data visualizatin experience independently came up with this design suggests that it has merit. I will gladly give Dan credit for being the first person to come up with this idea. I'll take credit only for refining it a bit, giving it a name, and making it known through my article.
Stephen Few

Posts: 4
Reply with quote  #3 
I put together an interactive wheat plot example in the Vega language, including options to explore different bin sizes and offsets. You can play with it here: https://vega.github.io/vega/examples/wheat-plot/



Posts: 1
Reply with quote  #4 
Thanx for this article, Steve. I am dealing with this right now at work. I have a scatterplot where the data points are sized according to a third dimension. Thus, 'big' dots cover up 'small' dots. This gives me ideas for fixing my graph.


visualReference, LLC
"Go From Numbers To Knowledge"

Posts: 194
Reply with quote  #5 
I've been using these for some time as well, and have had demos for making them in Highcharts for quite a while:

- http://jsfiddle.net/jlbriggs/e7k3ar4o/

- http://jsfiddle.net/jlbriggs/997j5ksk/

(though I started using them after seeing the post by Dan - I can't take any credit at all :) )


Posts: 44
Reply with quote  #6 
For anyone following this thread who might be interested, I started a thread in the Terminology area asking about the use "dodge" vs. "jitter".
Previous Topic | Next Topic

Quick Navigation:

Easily create a Forum Website with Website Toolbox.