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: Pairing predictors in tuples.
From
Eric Booth <[email protected]>
To
"<[email protected]>" <[email protected]>
Subject
Re: st: Pairing predictors in tuples.
Date
Mon, 2 Aug 2010 16:28:33 +0000
<>
Put x4 & x5 in quotes:
****!
clear
set obs 1000
forval n=1/5 {
g x`n' = rnormal()*100
}
g y = round(abs(rnormal()*1))
*****
tuples x1 x2 x3 "x4 x5"
forval i = 1/`ntuples'{
logit y `tuple`i''
di "`e(cmdline)'"
outreg2 using "test", append
}
****!
~ Eric
__
Eric A. Booth
Public Policy Research Institute
Texas A&M University
[email protected]
Office: +979.845.6754
On Aug 2, 2010, at 11:17 AM, Bradley Fedy wrote:
> Hi,
>
> I am using tuples to cycle through models using different subsets of
> predictors. My code looks something like this:
>
> tuples x1 x2 x3 x4 x5
> forval i = 1/31{
> logit y `tuple`i"
> }
>
> However, I do not want all possible combinations. I would like predictors
> x4 and x5 to always enter the model together (i.e. one cannot be present
> without the other).
>
> Any suggestions on how to make x4 and x5 always enter the model together
> would be greatly appreciated.
>
> Thanks,
> Brad
>
> Stata Ver. 10.1
>
>
> *
> * 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/
*
* 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/