« A reader's guide to a New York Times graphic | Main | High-effort graphics »



Regarding the new proposed chart, it is really easier to interpret and the data makes a lot more sense. My only problem with it is "connecting" the schools; following the lines doesn't mean anything, so the data should be unconnected dots.


Jeruza: You won't be the only reader to feel this way. Over the years, I have had complaints from readers about lines connecting categorical data every time I put up such a chart. Here's my reasoning: follow your eyes as you read a dot plot, you are visually tracing the lines that I have drawn, why not just draw the lines?

Stephanie Lee

I think the reason to not connect the lines is that, given the charts most of us see every day, we expect the x-axis on a line chart to be time. Despite knowing - very clearly - that it wasn't time, I still found myself thinking, "Why did they come together later on?" [Disclosure: I know nothing about basketball, so maybe this was just due to my ignorance.] I say: don't fight it! If people expect one thing and you're giving them something else, it's just a little bit harder for them to understand your message, which isn't what you want. That little difference with a dot plot not drawing the lines is just right: you don't automatically think, 'time series', but you can still follow along.


To add to what others have said, I would not necessarily expect the x-axis to be time, but I would expect it to display a metric variable, preferrably one which can be usefully interpreted as independent.


I tried an alternative approach here. The first and second highest and lowest are shown as a box and whisker plot. I know nothing about baseball, so I assume "the lane" is around the basket, and 3 point jump shots are more common than midrange.

While I'm with Kaiser on the complete acceptability of lines in category graphs (check out parallel coordinates for a graph type where this is not only okay, but vitally necessary) I am smug that a box and whisker chart doesn't have to worry about the controversy :-)


Kaiser, thanks for the reply. I can see your reasoning, but I'd argue that I don't actually "follow" the dots, I compare then. MAYBE I would be less whiny if there were big dots and subtle lines connecting them, hehe.

Still, I agree with Lemmus: if there are lines I expect x to mean something on its own.

But I promise to not fiercely fight about this on every single chart you ever post. Just on some. =]


I also liked Derek's suggestion, but for few data points I prefer Dot Plots to Box Plots. Like this: http://postimage.org/image/ne931c9hd/
(with a better label, of course; that's just me being lazy, sorry.

The problem with either one is comparing schools. If this was an academic paper it probably wouldn't be a big deal, but newspaper folk will need an far-from-the-chart label or names directly on the chart (Derek's approach).

dan l

Ahhh....the world wide leader screws something else up......


"my reasoning: follow your eyes as you read a dot plot, you are visually tracing the lines that I have drawn, why not just draw the lines?"

I think this is very poor reasoning.

A dot plot allows you to follow whatever path of comparison you choose, and does not imply a pattern that does not exist.

The line chart very explicitly instructs the user to follow the patter of the line, which in cases like this are completely without meaning of any kind.
It precludes the kind of comparisons that should be made with this data - how do the differences within each category compare, and how does this data point compare to the same data point in the other categories - not easy to do with this chart.

You are led to conclude that 3-pointers have really declined! :)

The argument of a parallel coordinates chart is not valid to justify a line chart like this either - parallel coordinates charts are very specific and use lines for very distinct purposes, where the pattern form *is* meaningful.

"I am smug that a box and whisker chart doesn't have to worry about the controversy"

Sorry, but I have to disagree with this as well :)
It depends on the goal of the visualization, of course, but a boxplot doesn't give us much meaning here either. It's great for portraying the distribution of each type of shot, but what do we learn from that in this particular application?


A dot plot, or a set of three bar charts would make the most sense for displaying this data in an easily comparable manner.


A couple of quick examples:
Dot Plot 1: http://jsfiddle.net/jlbriggs/FXaju/embedded/result/
Dot Plot 2: http://jsfiddle.net/jlbriggs/2T2ey/embedded/result/
Small Multiples: http://jsfiddle.net/jlbriggs/Mmd8N/embedded/result/

I believe all three examples better facilitate relevant comparisons between values and categories.

The comments to this entry are closed.


Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
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