« A luxury we can afford to miss | Main | Radar charts, Ripleyesque replies, and straight-ticket votes »


Tom West

So the actual intersting story is in the variance, not the mean - i.e. why does the NBA have such a wide range of home advantages compared with the MLB and NHL.

Alex Reutter

Note that the NBA also has a wider range of overall winning percentages; I think you would need to compare the variance in the home winning percentages to the overall winning percentages across the sports to see if anything special is happening with home advantage in the NBA.

It would be neat to see the 2000-2009 data plotted to expose whether there's any variation in the variation over time.


I don't get your point. If I understand correctly you say that the Nationals won 36% of their matches, the Yankees 65%, etc. But if that winning percentage was always the same, independently of playing at home or away, there would be no home bias when averaging over all the matches. In the other extreme, suppose the local team always wins: the winning percentage for the home team would be 100% but the winning percentage for each team would be 50%. The variability that you show is interesting, but it's not clear to me what is the relation with the home bias displayed in the original chart.


Carlitos: First, your comment makes me realize that I don't have home-team winning percentages; what I have are overall winning percentages. However, my point about needing to know the variability to understand averages still stands.

What the graph seems to be doing is to contrast the home-team winning percentages for different sports. We observe a difference of average WP of about 5 to 10%. As reader, I'd like to understand whether a 5% difference is a "big deal" or not. And the variability gives us the context. By contrast, the pie chart construct gives us the wrong context because it draws attention to the 0-100% range which is mostly irrelevant.

Sean Houghton

Doesn't including a sentence on how to read the chart mean that you've just failed the self sufficiency test as well?


I do not understand. If you realize that you "don't have home-team winning percentages" but only "overall winning percentages", how is possible that "the graph seems to be doing is to contrast the home-team winning percentages for different sports"?
IMHO the larger variability for NBA (in overall winning percentages which your box-plot graph shows) is simply due to a larger variability in team strengths: the difference between the strongest team and the weakest team is larger than in MLB and NHL.

İşyeri Sigortası

good work for best job thanx u for admin.

Kasko Sigorta

interesting work :/

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