Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: rxridge


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: rxridge
Date   Tue, 13 Sep 2005 11:08:25 +0100

As mentioned on this list recently, you should 
say where programs other than those in official 
Stata come from. 

The program -rxridge- was written by R.L. Obenchain 
and published in STB-28 in 1995. There is also
a more recent version by William Gould on the 
StataCorp website, which contains a work-around 
for problems arising with the program in Stata 6. 
The author does not appear to be active in the Stata 
community. There was some question a few years back about updating 
this program further, but nothing happened as
far as I can see. 

-rxridge- uses a very outdated way of saving datasets 
it is working with in named files in the current 
directory. 

In your case, you may be using Stata in a directory 
in which you have no write access. That is a very 
wild guess. 

Nick 
n.j.cox@durham.ac.uk 

Sriram Narayanan
 
> I want to know more about ridge regression in stata. I
> actually am working with some data that seems to be
> highly multicollinear. I looked up the literature that
> ridge regression could be onne way to estimate the
> pareameters. 
> 
> I am tryinf the dollowing command
> 
> rxridge y x1 x2 x3
> 
> in my case it terminates with the following message.
> 
> 
> RXridge:  Shrinkage Coefficients...
> obs was 0, now 25
> (18 missing values generated)
> (note: file rxridge1.dta not found)
> file rxridge1.dta could not be opened
> r(603);
> 
> 
>  This might be a very dumb question but I will be very
> grateful for a response.

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



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