Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: mosaic plot with an intensity dimension


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: mosaic plot with an intensity dimension
Date   Fri, 24 Feb 2012 15:17:55 +0000

-spineplot- is from SJ. Please remember to explain _where_ user-written programs you refer to come from. 

I don't think the literature on graphics is encouraging on quantitative decoding of colour intensity. Either way, as you know, -spineplot- does not support what you want directly. 

An alternative plot that is quite easy to arrange, but may or may not work well, is 

egen group = group(y x), label
spineplot z group 

Nick 
n.j.cox@durham.ac.uk 

Dimitriy V. Masterov

I would am trying to create the graph of customer data where y is
categorical customer type (4 integer values), x is binary new customer
variable, and z is a binary purchased or not variable. I would like to
create a mosaic plot of y and x to show the sizes of the groups, but
somehow express the percentage of customers who purchase the product
for each group using color intensity. I want to show that some group
has a really high purchase rate, but they are a small fraction of the
customers. Right now I do this with user-written spineplot using the
text option:

bys type new_cust: egen mean=mean(reorder_90)
replace mean=mean*100
gen mean2=string(mean, "%4.0f")
spineplot type new_cust, text(mean2) percent

This uses numbers rather than color intensity, and is harder to read
or to see patterns, at least for my brain. A rough example of what I
want to see is http://newsmap.jp, where the color intensity indicates
the number of related articles.

Is there a way of expressing the mean with color intensity? Is there a
better way of visualizing this data?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index