Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: overlaying 2 or more ciplot/option nolconfidence?

From   josemaria <>
Subject   Re: st: RE: overlaying 2 or more ciplot/option nolconfidence?
Date   Sun, 23 Nov 2003 21:24:04 -0200

Dear Nick:
Thank you for your kindness. Yes, you are right. I have a categorical variable, say A, with 3 categories, A1, A2, A3. The idea was to plot the means of the continuous variable haemoglobin over the values 0,1,2,3 ..11 months of the numeric/continuous variable age. So, I would have three curves of haemoglobin in the same plot/graph. In using -ciplot- I would do it very fast if the command allowed that.
I will try the other ways.
Jose Maria

Nick Cox wrote:

I take this as a reference to the user-written program -ciplot- on SSC. > -ciplot- is best thought of as a wrapper for -ci-. It has a -by()- option, just
as -ci- does, and the design decision was to allow several confidence intervals to be shown in one plot.
That _isn't_ how -twoway ... , by()- works; in other words, -ciplot- follows
-ci-, not -twoway-, in what -by()- means.
-ciplot- has a -plot()- option, which is more evident from looking at the code
than from looking at the help,
As the whole point of -ciplot- is to draw confidence intervals, I am somewhat bemused
by the option suggested. If you want just to plot means, there are lots of ways
to do that.
Jose Maria Pacheco de Souza, Professor Titular
Departamento de Epidemiologia
Faculdade de Saude Publica/Universidade de Sao Paulo
Av. Dr. Arnaldo, 715	cep 01246-904
Sao Paulo	Brasil
fones (11)3082-3886  (11)3714-2403  (11)3768-8612
fax   (11)3082-2920  (11)3714-2403

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index