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: Useful labelling of dummy variables following logit
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: Useful labelling of dummy variables following logit
Date
Wed, 24 Aug 2011 16:54:29 +0100
Are you talking about this code or your equivalent on your problem?
If the latter, I need to see the code to comment helpfully.
Nick
On Wed, Aug 24, 2011 at 4:41 PM, Tim Evans <[email protected]> wrote:
> Nick,
>
> Thanks for this, it nearly works for me - I can graph it, but I don't get all of the variable values from the 'axis' column to appear - I only have random ones. Do you know why it does not display all of the variables names (but does display the estimate value)
>
> Tim
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Nick Cox
> Sent: 24 August 2011 14:31
> To: [email protected]
> Subject: Re: st: Useful labelling of dummy variables following logit
>
> Maarten's example doesn't show variable labels. Here is one way to do
> it. I may well be overlooking an option in -parmest-.
>
> Nick
>
> sysuse nlsw88, clear
> logit union married never_married collgrad south
>
> local i = 0
> foreach v in married never_married collgrad south {
> local l`v' : variable label `v'
> }
>
> parmest, norestore eform
> foreach v in married never_married collgrad south {
> replace parm = "`l`v''" if parm == "`v'"
> }
>
> replace parm = "(intercept)" if parm == "_cons"
>
> egen axis= axis(estimate), label(parm)
>
> twoway bar estimate axis, base(1) horizontal barw(.5) ///
> xline(1) ylab(, valuelabel ang(h) noticks) || ///
> rcap min95 max95 axis, horizontal ///
> legend(order(1 "point estimate" ///
> 2 "95% conf. int.") pos(6)) ///
> xtitle("odds ratio") ytitle("")
>
>
> On Wed, Aug 24, 2011 at 2:03 PM, Maarten Buis <[email protected]> wrote:
>> On Wed, Aug 24, 2011 at 2:56 PM, Tim Evans <[email protected]> wrote:
>>> Nick, in your last post, are you suggesting an alternative way of presenting things as I'm not sure I follow what you mean by:
>>>
>>> ' I'd much prefer to work at a graphical display of odds
>>> ratios and confidence limits with variable labels as horizontal text'
>>
>> See, e.g. <http://www.stata.com/statalist/archive/2010-09/msg00525.html>
*
* 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/