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 on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Syntax to specify clustering on a variable or turn off clustering


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Syntax to specify clustering on a variable or turn off clustering
Date   Wed, 27 Mar 2013 16:51:44 +0000

Have a look at

SJ-9-3  pr0048  . . . . . . . . .  Stata tip 79: Optional arguments to options
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N. J. Cox
        Q3/09   SJ 9(3):504                                      (no commands)
        tip showing programmers how to provide an option that
        can be specified with or without arguments

http://www.stata-journal.com/sjpdf.html?articlenum=pr0048

Nick

On Wed, Mar 27, 2013 at 4:41 PM, Nicholas Potter
<potter.nicholas@gmail.com> wrote:

> I'm trying to write a program that will use clustering on a variable by
> default, but also give the user the option to turn it off or to cluster on
> a different variable. The problem is that including both "cluster(varname)"
> and "nocluster" in the syntax definition results in the cluster option not
> being stored.
>
> For example:
>
> program define regress2
>
> syntax varlist [if] [in] [aw fw iw/] [, cluster(passthru) nocluster ]
> ...
> if "`cluster'"=="nocluster" {
>   reg yvar xvars
> }
> else if "`cluster'"=="" {
>   reg yvar xvars, cluster(foriegn)
> }
> else {
>   reg yvar xvars, `cluster'
> }
>
> end
>
> This will default to cluster(foreign) regardless of whether a
> cluster(varname) option is passed:
>
> webuse auto, clear
> regress2 price mpg rep78 --> program clusters on foreign
> regress2 price mpg rep78, cluster(make) --> program clusters on foreign
> regress2 price mpg rep78, nocluster --> no clustering is used
>
>
> the second command should cluster on make instead of on foreign.
>
> Any thoughts or recommendations? I could change nocluster to clusteroff or
> something, but that wouldn't be in keeping with stata syntax convention.
*
*   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