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: RE thread: SEM with categorical variables


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE thread: SEM with categorical variables
Date   Wed, 13 Mar 2013 12:48:39 -0500

The code does not run not because of the -clear- command, but because your
local `N' is defined only in the first do-file, and cannot be accessed by
the second one. With locals, don't try cheat and run pieces of code, put
everything into a single file and run it top to bottom. (Your previous
problem was likely of similar nature that you ran your lines from the
do-editor by selecting a few lines and sending them to Stata; that way,
later lines have no idea about locals defined in earlier files, as these
locals died when the do-files exited.)

-- Stas Kolenikov, PhD, PStat (SSC)
-- Senior Survey Statistician, Abt SRBI
-- Opinions stated in this email are mine only, and do not reflect the
position of my employer
-- http://stas.kolenikov.name



On Wed, Mar 13, 2013 at 10:06 AM, Laura Maria Schwirz <schwirzl@tcd.ie>
wrote:
>
> Thanks for quick reply. It actually works up to a certain point..
> local thevars hewsonstrong hewsonknowo hewsonint hewsoninspi
> hewsonmoral hewsoncom hewsondecent hewsondepend hewsonrel hewsonsens
>
> . polychoric `thevars'
>
> Polychoric correlation matrix
>
> (output omitted)
>
> . mat polychR = r(R)
>
> .  forvalues i=1/`: word count `thevars' ' {
>   2.  forvalues j=1/`i' {
>   3.  local setcor `setcor' `=polychR[`i',`j']'
>   4.  }
>   5.  if `i' < `: word count `thevars' ' local setcor `setcor' \
>   6.  }
>
> .  local N = _N
>
> .
> end of do-file
>
> . do "/var/folders/lw/lweDBBEGH68nFpOhV2D+gk+++TI/-Tmp-//SD00459.000000"
>
> .  clear
>
> .  ssd init hewsonstrong hewsonknowo hewsonint hewsoninspi hewsonmoral
> hewsoncom hewsondecent hewsonde
> > pend hewsonrel hewsonsens
>
> Summary statistics data initialized.  Next use, in any order,
>
>     ssd set observations (required)
>         It is best to do this first.
>
>     ssd set means (optional)
>         Default setting is 0.
>
>     ssd set variances or ssd set sd (optional)
>         Use this only if you have set or will set correlations and,
> even then, this is optional but
>         highly recommended.  Default setting is 1.
>
>     ssd set covariances or ssd set correlations (required)
>
> .  ssd set obs `N'
> number required
> r(100);
>
> Once I run the 'clear' command, it stops working.
>
> Many thanks for your help, much appreciated.
>
> Laura
>
>
> On 13 March 2013 14:42, William Buchanan <william@williambuchanan.net>
> wrote:
> >
> > I don't think it's a problem with Stas's code:
> >
> > clear
> > set obs 1000
> > set seed 123412345
> > loc thevars hewsonstrong hewsonknowo hewsonint hewsoninspi hewsonmoral
> > hewsoncom hewsondecent hewsondepend hewsonrel hewsonsens
> > foreach v of loc thevars {
> >         qui: g id=runiform()
> >         qui: sort id
> >         /* Create categorical variables */
> >         qui: egen `v' = cut(id), group(5)
> >         /* Recode the variables to have a scale of 1-5 */
> >         qui: replace `v'=`v'+1
> >         qui: drop id
> >         ta `v'
> > }
> > di `"`thevars'"'
> > polychoric `thevars'
> >
> > You should get the matrix below:
> >
> > hewsonstrong   hewsonknowo     hewsonint   hewsoninspi   hewsonmoral
> > hewsoncom  hewsondecent  hewsondepend     hewsonrel    hewsonsens
> > hewsonstrong             1
> >  hewsonknowo     .00757784             1
> >    hewsonint    -.01262061    -.02690757             1
> >  hewsoninspi    -.02231892     .00686848    -.05248286             1
> >  hewsonmoral    -.01757277     .03654591    -.01172315     .00876538
> > 1
> >    hewsoncom     .02118915    -.01551056    -.01772426    -.00254414
> > -.01837419             1
> > hewsondecent    -.04116923     .01386142     .01676589     .02919821
> > .02132269    -.03298761             1
> > hewsondepend    -.05280085    -.04659978     .04573638     .01585641
> > .06480197    -.01835768    -.02216604             1
> >    hewsonrel     .02682836    -.00184872    -.00382025     .01606113
> > -.03550408     -.0348673     .06411171    -.02613873             1
> >   hewsonsens     .02954704     -.0527784     .01723573    -.06313792
> > .00313384     .01654635     .02302709    -.00659043     -.0318338
> > 1
> >
> >
> >
> >
> > On Mar 13, 2013, at 7:21 AM, Laura Maria Schwirz <schwirzl@tcd.ie>
> > wrote:
> >
> > > I am referring to a previous thread (RE: sem with categorical
> > > variables, September 2012) as I have similar problems. I tried using
> > > Stas' code for polychoric to sem analysis but the local command
> > > appears to be a problem. If I type
> > >
> > >> local thevars hewsonstrong hewsonknowo hewsonint hewsoninspi
> > >> hewsonmoral hewsoncom hewsondecent hewsondepend hewsonrel hewsonsens
> > >> display `thevars'
> > >> polychoric `thevars'
> > > varlist required
> > >
> > > It as actually empty so i can't proceed with the polychor command
> > > Any thoughts/ideas of where I am going wrong?
> > >
> > > Thanks,
> > > Laura
> > > *
> > > *   For searches and help try:
> > > *   http://www.stata.com/help.cgi?search
> > > *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
> > *   http://www.ats.ucla.edu/stat/stata/
> >
>
>
>
> --
> Laura Schwirz
>
> PhD Candidate and IRCHSS Scholar
> Department of Political Science
> Trinity College Dublin
> Dublin 2
> Republic of Ireland
> Email: schwirzl@tcd.ie
>
>
>
> --
> Laura Schwirz
>
> PhD Candidate and IRCHSS Scholar
> Department of Political Science
> Trinity College Dublin
> Dublin 2
> Republic of Ireland
> Email: schwirzl@tcd.ie
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index