I am about to start studying the code for building boxplots with SAS. I noticed there are many ways or procedures to build them. Which one is best for the following?
I wish to do a box plot for 10 groups of data, side-by-side. I thijnk that will be easy enough. I am not really interested in the fanciness of the graphics, but I am sure that will come in time.
I also wish to vary the end points for my whiskers or outliers. For example, I believe the standard box plot pushes the outer fences to 1.5 X the IQR. I would like the option of seeing the data at 2 X IQR range or 3 X IQR as well. Or, maybe perhaps specify the percentiles.
Thank you very much in advance.
That is great information from both of you guys! Thank you so much.
Now the problem I am dealing with is my scatterplots are skewed in a major way. Wihin each of the 10 categories the majority of the points are zero - no longer thinking boxplots would be terribly conducive to understanding such a skewed distribution.
Any other suggestions to graphically see what is going on in a snapshot? If I were to just send out my percentiles an example for one of my categories could be:
Can anyone think of a way to adjust such scatterplots in these situations? Perhaps put a condition in that the value needs to be > 0 - but then I am steering away from the original question.
With SAS 9.4M2, you can overlay scatter plot on a BoxPlot. Would that help?
Here, for many observations (chosen randomly), I made mpg_city=missing, and mpg=0 for the same.
Then I plotted a box plot of mpg_city, overlaid with a scatter plot of mpg with JITTER.
Does this help?
if ranuni(2) < 0.7 then do;
proc sgplot data=cars noautolegend;
vbox mpg_city / category=type;
scatter x=type y=mpg / jitter;
Registration is open! SAS is returning to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team. Register for just $495 by 12/31/2023.
If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.