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: problem using "vselect"


From   clindsey@stata.com
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: problem using "vselect"
Date   Fri, 28 Jun 2013 16:41:01 -0500

Matthew Hamilton <mwhamilton@gmail.com> has a problem using the -vselect-
command. 

>Hi, I'm using the vselect package as follows:
>
>vselect depvar varlist, fix(indepvar1 indepvar2) best
>
>"Varlist" stands for a long list of candidate predictors. This list does not
>include indepvar1, indepvar2, or depvar. My understanding is that the option
>fix(indepvar1 indepvar2) forces the algorithm to give the "best" model that
>contains those two variables for each quantity of predictors. For example:
>
>vselect logI2010pc logGCI7_LaborMarketEfficiency
>logGovcontrolofcorruption logLFPR2010, fix(logGDP2010pc logWA2010pc)
>best
>
>However, I keep getting the error: "The Fixed variables overlap with
>the predictors/response."
>
>Based on my reading of vselect.ado, I am pretty sure it is supposed to
>give this error when varlist and the fix() vars are not disjoint.
>What's going on? Could this be a bug in vselect?

We were unable to replicate Matthew's error.  -vselect- was updated in 2011 to
correct a bug related to the -fix()- option.  Maybe Matthew's version of
-vselect- is out of date.   Matthew can get the current version of -vselect- 
by typing

  . adoupdate st0213, update

Charles Lindsey
Senior Statistician and Software Developer
StataCorp
clindsey@stata.com 
*
*   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