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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: Plotting regression constants


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Plotting regression constants
Date   Sun, 7 Aug 2011 21:16:46 +0100

Please define "a more traditional box-and-whisker plot". -graph box-
implements a standard Tukey design. What else do you seek?

Nick

On Sun, Aug 7, 2011 at 7:32 PM, Jennifer M Keister <jkeister@ucsd.edu> wrote:
> Christophe,
>
> Thank you for your (extremely prompt) response!
>
> I think we are part-way there on this problem, but I still have a few issues.  I am pretty unfamiliar with writing code directly in Stata, so please enlighten any rookie mistakes I am making in my syntax.  Let me provide a little more information than I did in my original post.
>
> Prior to my posting, I have been using the following syntax to estimate a set of equations:
> foreach v of varlist *var {
> quietly svy: reg `v' <covariates>
> estimates store `v'var, title(`v')
> }
> estout *var using vartable.txt, cells(b(star fmt(3)) se(fmt(3))) starlevels(* 0.10 ** 0.05 *** 0.01) keep(_cons)
>
> As mentioned, I would like to produce a graph of the constants rather than this set of numerical columns produced by the -estout-command.
>
> I have tried the syntax you suggest for a single equation:
> quietly svy: reg `v' <covariates>
> mat b = e(b)
> local eqlist : coleq b
> di "`eqlist'"
> local eqlist : list uniq eqlist
> di "`eqlist'"
> gen b_cons=.
> local i=1
> foreach x of local eqlist {
> replace b_cons=_b[`x':_cons] if _n==`i++'
> }
>
> graph box b_cons
>
> This gives me graph with a y-axis with a range from the lower to upper quartiles, and a horizontal line at the median value for the constant.  I was hoping I could produce a more traditional box-and-whisker plot.  Is there a way to do this?
>
> Also, is there a way to wed the plotting syntax you suggest into the estimation loop I have been using, so that I can look at a graphic version of the -estout- table I've produced thus far and see the constants for all of the equations?
>

*
*   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