# Re: RE: st: Regression: All possible subsets

 From Robert A Yaffee <[email protected]> To [email protected] Subject Re: RE: st: Regression: All possible subsets Date Sun, 26 Nov 2006 00:18:16 -0500

```Joe,
Try ssc describe a
Then to install allpossible, type:
ssc install allpossible
- RY

Robert A. Yaffee, Ph.D.
Research Professor
Shirley M. Ehrenkranz
School of Social Work
New York University

Apt 19-W
2100 Linwood Ave.
Fort Lee, NJ
07024-3171
Phone: 201-242-3824
Fax: 201-242-3825
[email protected]

----- Original Message -----
From: Joseph Coveney <[email protected]>
Date: Saturday, November 25, 2006 9:48 pm
Subject: Re: RE: st: Regression: All possible subsets

> Raphael Fraser wrote:
>
> tryem has no help file. I threw some variables at it and it froze.
> Nick?? Are you there?
>
> --------------------------------------------------------------------
> ------------
>
> Hmmm . . . -findit- doesn't bring up either -tryem- or -allpossible-.
>
> -tryem- is an older module by Al Feiveson; -allpossible- is the one
> by Nick
> Cox.  -tryem- does linear regression.  -allpossible- is more general.
>
> In any event, there is a help file for -tryem- on my machine
> (printed out
> below after the example of its use).  I'm not sure why it's not
> there on SSC
> anymore.  The help file mentions that you'll need to have
> installed -mktime-.
>
> Joseph Coveney
>
> . clear
>
> . set more off
>
> . set obs 7
> obs was 0, now 7
>
> . forvalues i = 1/7 {
>  2. generate float a`i' = 0.5 + 0.5 * (`i' == _n)
>  3. }
>
> . mkmat a*, matrix(A)
>
> . drawnorm y x1 x2 x3 x4 x5 x6, corr(A) n(25) seed(`=date("2006-11-
> 26","ymd")') clear
> (obs 25)
>
> . forvalues i = 5(-1)1 {
>  2. tryem y x1 x2 x3 x4 x5 x6 `i'
>  3. }
> n = 6
> var =  y    x1    x2    x3    x4    x5    x6    5
> --------------------------------------------
>
>  1  3  4  5  6
>    .300381  best of size 5
> subset is x1 x3 x4 x5 x6
> --------------------------------------------
> n = 6
> var =  y    x1    x2    x3    x4    x5    x6    4
> --------------------------------------------
>
>  1  3  4  6
>    .299128  best of size 4
> subset is x1 x3 x4 x6
> --------------------------------------------
> n = 6
> var =  y    x1    x2    x3    x4    x5    x6    3
> --------------------------------------------
>
>  1  4  6
>    .296403  best of size 3
> subset is x1 x4 x6
> --------------------------------------------
> n = 6
> var =  y    x1    x2    x3    x4    x5    x6    2
> --------------------------------------------
>
>  1  6
>    .291414  best of size 2
> subset is x1 x6
> --------------------------------------------
> n = 6
> var =  y    x1    x2    x3    x4    x5    x6    1
> --------------------------------------------
>
>  6
>    .201019  best of size 1
> subset is x6
> --------------------------------------------
>
> . chelp tryem
>
> --------------------------------------------------------------------
> ------------------------------------
>
> Help file for the command tryem
> --------------------------------
>
> Syntax
> ------
>
> tryem var varlist k
>
>
> Options
> -------
>
> Description
> -----------
> 'TRYEM': module to run all possible subset regressions
> tryem calculates all possible regressions of a given subset size.
> The maximum number of subsets, k, is one fewer than the total
> number of
> independent variables.
> The module mktime is required.
>
> tryem finds best regression subset of size k by brute force.
> It assumes independent variables are x1-xn and dependent variable
> is y
> `1' = dep;   `2',..`nv+1' are indeps `nv+2'=k
>
>
>
> Examples
> --------
> Example: tryem yyy xvar1 xvar2 xvar3 xvar4 2  finds best 2-subset
> regressionof
> yyy on 4 indep variables xvar1,xvar2,xvar3,xvar4
>
>
> Author(s)
> ---------
>
> Al Feiveson, Johnson Spaceflight Center
> Email: [email protected]
>
> Also see
> --------
>
>
> --------------------------------------------------------------------
> ------------------------------------
>
> .
>
> *
> *   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/
>
*
*   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/
```