LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (May 2006, week 4)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Sun, 21 May 2006 22:53:01 -0700
Reply-To:     David L Cassell <davidlcassell@MSN.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         David L Cassell <davidlcassell@MSN.COM>
Subject:      Re: Creating combinations in SAS
In-Reply-To:  <200605211258.k4LAlaVZ004671@mailgw.cc.uga.edu>
Content-Type: text/plain; format=flowed

rdevenezia@WILDBLUE.NET replied: >saurabh wrote: > > Hi All , > > > > I am new to SAS, however I am asked to do some work beyond that > > knowledge level and its going over my head and understanding . ok > > lets get to it .... > > > > Ok the present method what I am doing is .... > > > > I have a set of 20 variables. I need combinations of 4 each. > > 1. creating a combination of those 20 variables. this should come out > > into a data set. > >Perhaps in future releases of SAS there will be an ALLCOMB function.

I have heard rumors that such a function may appear one of these days.

>In the meantime, a simple m-m-m-m-macro can enumerate all the combinations >by generating a DATA Step source code that contains the requisite number of >nested and properly bounded loops. > >%macro allcomb (n=6,k=3); > data combos_&n._&k.; > i0=0; > %do i = 1 %to &k; > do i&i = i%eval(&i-1)+1 to %eval(&n-&k+&i); > %end; > output; > n+1; > %do i = 1 %to &k; > end; > %end; > drop i0; > run; >%mend; > >options mprint; > >%allcomb(n=20,k=4);

But this is not needed for PROC REG. Just look at the SELECTION= options.

Or don't. Let's pretend there is no such option. It was all a bad dream. :-) :-)

> > 2. running proc reg on the combinations , by picking up each variable > > to be a dependant variable and running proc reg on those 4895 > > combinations . With all values of Proc Reg coming out ( ie R Sqaure > > and Adj R Square and the test of significance ) into a dataset. > >Someone, somewhere in the world has blanched and is turning an awful shade >a >green.

That would be me.

David -- David L. Cassell mathematical statistician Design Pathways 3115 NW Norwood Pl. Corvallis OR 97330

_________________________________________________________________ Don’t just search. Find. Check out the new MSN Search! http://search.msn.click-url.com/go/onm00200636ave/direct/01/


Back to: Top of message | Previous page | Main SAS-L page