Timeline for Boxplot equivalent for heavy-tailed distributions?
Current License: CC BY-SA 3.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 3, 2013 at 20:50 | vote | accept | static_rtti | ||
| Jul 9, 2013 at 7:18 | |||||
| Jul 3, 2013 at 15:52 | comment | added | Nick Cox | +1. If you want to use boxplots, there is no problem in principle with skewed distributions, but in practice they are not very helpful; so transformation is a good idea. In general, I often have found quantile-quantile plots useful, but you have to find out which congenial distribution fits adequately. | |
| Jul 3, 2013 at 15:12 | comment | added | whuber♦ | My answer was posted at stats.stackexchange.com/questions/13086, which I view as an (inconsequentially narrower) version of this question. I summarized it as "don't change the boxplot algorithm: re-express the data instead." The issue hinted at by the "adapted" in this question is addressed by standard techniques of Exploratory Data Analysis for finding helpful re-expressions of variables. | |
| Jul 3, 2013 at 15:07 | comment | added | TooTone | @Whuber thanks for explaining further. I'd welcome an answer from either you or Nick. | |
| Jul 3, 2013 at 14:41 | comment | added | Nick Cox | @Whuber Thanks for trying to summarize. Sometimes one does needs a graph showing the clustering explicitly. To go beyond that, one often needs something else. I don't think there can be a universal solution e.g. if there are zeros logarithms are often a bad idea, although some people are happy to fudge to log(x + 1). | |
| Jul 3, 2013 at 14:38 | comment | added | whuber♦ | I believe the motivation behind @Nick Cox's comments is that all the methods presented in this answer are seen to be unhelpful when applied to heavy-tailed data: they all produce clusters of points at one end of the plot (or, in the case of Q-Q plots, a nearly horizontal line) and one or a few sparse points at the other end, merely confirming what was known at the outset: a tail is heavy. An effective solution would both reveal the heaviness of the tails and effectively resolve the main mass of data. | |
| Jul 3, 2013 at 14:28 | history | edited | TooTone | CC BY-SA 3.0 |
added beeswarm
|
| Jul 3, 2013 at 14:25 | comment | added | TooTone | @January Yeah that's pretty cool, I'm adding it to my answer (if you object please say so). | |
| Jul 3, 2013 at 14:06 | comment | added | January |
Even better than stripplots from R are the plots from the beeswarm package.
|
|
| Jul 3, 2013 at 12:48 | comment | added | TooTone | @NickCox I also found your comments re transformations on the other answer illuminating. | |
| Jul 3, 2013 at 11:03 | comment | added | Nick Cox | The point is just that the advice to use e.g. qqnorm does not match the question. Other kinds of quantile-quantile plots could, I agree, be a very good idea, as I mentioned earlier. | |
| Jul 3, 2013 at 10:59 | comment | added | TooTone | @NickCox I would still use stripplots here as a first cut. I'd definitely be interested in other answers though, as I have come across similar problems to the OP in the past. | |
| Jul 3, 2013 at 10:57 | comment | added | Nick Cox | I like stripplots too, but the question is explicitly about what to do with heavy-tailed distributions. | |
| Jul 3, 2013 at 10:28 | history | answered | TooTone | CC BY-SA 3.0 |