Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: marginsplot is acting differently
From
[email protected] (Jeff Pitblado, StataCorp LP)
To
[email protected]
Subject
Re: st: marginsplot is acting differently
Date
Tue, 03 Jan 2012 18:02:35 -0600
Richard Williams <[email protected]> noticed an unintentional
behavior change to -marginsplot- after -margins- with factor variables in the
-dydx()- option (introduced in the 13oct2011 update):
> -marginsplot- seems to be acting differently than it was a few months
> ago, and the change is not for the better. Here is my code:
>
> webuse nhanes2f, clear
> logit diabetes i.black i.female age, nolog
> margins, dydx(black female) at(age=(20 30 40 50 60 70)) vsquish
> marginsplot, noci
>
> When I ran this a few months ago, I got a line for 1.black and
> 1.female, which is what I want. But, when I run it now, I also get
> lines for 0b.black and 0b.female. The latter are worthless because
> they are simply the same as the X axis, i.e. the effects are always 0.
>
> I am guessing this is some sort of bug and if so I hope it will be
> fixed soon. But in the meantime, does anybody know an easy way to get
> only the two lines that I want? I can go into the graph editor and
> hide things but that is a pain.
>
> I have a feeling this isn't the best time to ask a question, but I'll
> keep my fingers crossed that somebody is working late before taking
> some richly deserved time off for the New Year!
Philip Ryan <[email protected]> posted a work-around that did not
involve using the graph editor.
We have determined the cause of this unintentional behavior and fixed it.
The fix should be available in the next update to Stata 12.
--Jeff
[email protected]
*
* 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/