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: Factor variables and outreg/outreg2
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: Factor variables and outreg/outreg2
Date
Sat, 3 Mar 2012 09:48:03 +0000
For clarity:
1. -outreg- (John Gallup, SSC) and -outreg2- (Roy Wada, SSC) are now
quite different programs by quite different authors.
2. Both are user-written and so (once again) people referring to them
are requested to make that clear.
Nick
On Fri, Mar 2, 2012 at 9:25 PM, Richard Williams
<[email protected]> wrote:
> At 03:49 PM 3/2/2012, Schmidt, William wrote:
>>
>> I am attempting to use outreg2 but I would like to report a limited set of
>> covariates. I have factor variables in my regression, and they seem to be
>> ignored by the options in outreg. In the example below, for instance,
>> i.foreign##c.weight is not reported.
>>
>> sysuse auto, clear
>> regress mpg i.foreign##c.weight i.rep78 headroom
>> outreg2 using myfile, keep(i.foreign##c.weight headroom) sortvar(headroom
>> i.foreign##c.weight)
>
>
> This isn't quite right but it may be closer to what you want.
>
> outreg2 using myfile, keep(1.foreign#c.weight headroom) sortvar(headroom
> i.foreign#c.weight)
>
> Personally, I tend to avoid the ## notation and instead write stuff like
>
> regress mpg i.foreign weight i.foreign#c.weight i.rep78 headroom
>
> It may take more typing but it helps me to keep straight what I am doing.
> Plus, in various post-estimation commands, you often have to write things
> like 1.foreign rather than i.foreign. Look at how the regress command
> labeled each line of the output.
*
* 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/