Normalization in SAS
in [SAS]
|
From: ANNlearner on 16 Sep 2006 18:26 Is there a convenient way to normalize a set of variables, such as command "prestd" of matlab? I know that we can track the mean and standard deviation of each variable, and calculate the normalized values by subtract mean and divide standard deviation, however, this method is not concise, especially when there are about ten variables. Thanks a lot!
From: "Howard Schreier <hs AT dc-sug DOT org>" on 16 Sep 2006 20:13 PROC STANDARD On Sat, 16 Sep 2006 15:26:08 -0700, ANNlearner <lizhe01(a)GMAIL.COM> wrote: >Is there a convenient way to normalize a set of variables, such as >command "prestd" of matlab? I know that we can track the mean and >standard deviation of each variable, and calculate the normalized >values by subtract mean and divide standard deviation, however, this >method is not concise, especially when there are about ten variables. > >Thanks a lot!
From: NordlDJ on 16 Sep 2006 20:17 > -----Original Message----- > From: SAS(r) Discussion [mailto:SAS-L(a)LISTSERV.UGA.EDU] On Behalf Of > Howard Schreier <hs AT dc-sug DOT org> > Sent: Saturday, September 16, 2006 5:14 PM > To: SAS-L(a)LISTSERV.UGA.EDU > Subject: Re: Normalization in SAS > > PROC STANDARD > > On Sat, 16 Sep 2006 15:26:08 -0700, ANNlearner <lizhe01(a)GMAIL.COM> wrote: > > >Is there a convenient way to normalize a set of variables, such as > >command "prestd" of matlab? I know that we can track the mean and > >standard deviation of each variable, and calculate the normalized > >values by subtract mean and divide standard deviation, however, this > >method is not concise, especially when there are about ten variables. > > > >Thanks a lot! Or if you don't have the ETS module but do have STAT module, then PROC STDIZE. Hope this is helpful, Dan Daniel J. Nordlund Research and Data Analysis Washington State Department of Social and Health Services Olympia, WA 98504-5204
From: David L Cassell on 18 Sep 2006 02:20 NordlDJ(a)DSHS.WA.GOV wrote: > > > -----Original Message----- > > From: SAS(r) Discussion [mailto:SAS-L(a)LISTSERV.UGA.EDU] On Behalf Of > > Howard Schreier <hs AT dc-sug DOT org> > > Sent: Saturday, September 16, 2006 5:14 PM > > To: SAS-L(a)LISTSERV.UGA.EDU > > Subject: Re: Normalization in SAS > > > > PROC STANDARD > > > > On Sat, 16 Sep 2006 15:26:08 -0700, ANNlearner <lizhe01(a)GMAIL.COM> >wrote: > > > > >Is there a convenient way to normalize a set of variables, such as > > >command "prestd" of matlab? I know that we can track the mean and > > >standard deviation of each variable, and calculate the normalized > > >values by subtract mean and divide standard deviation, however, this > > >method is not concise, especially when there are about ten variables. > > > > > >Thanks a lot! > >Or if you don't have the ETS module but do have STAT module, then PROC >STDIZE. > >Hope this is helpful, > >Dan Umm, Dan, I believe that PROC STANDARD is in Base SAS. So everyone has it. Still, PROC STDIZE is a good tool to have in the toolbox. It does a lot more than PROC STANDARD, and provides robust and resistant measures of location and spread to do the normalization. HTCT, David -- David L. Cassell mathematical statistician Design Pathways 3115 NW Norwood Pl. Corvallis OR 97330 _________________________________________________________________ All-in-one security and maintenance for your PC. Get a free 90-day trial! http://www.windowsonecare.com/trial.aspx?sc_cid=msn_hotmail
From: NordlDJ on 18 Sep 2006 14:04 > -----Original Message----- > From: SAS(r) Discussion [mailto:SAS-L(a)LISTSERV.UGA.EDU] On Behalf Of David > L Cassell > Sent: Sunday, September 17, 2006 11:21 PM > To: SAS-L(a)LISTSERV.UGA.EDU > Subject: Re: Normalization in SAS > > NordlDJ(a)DSHS.WA.GOV wrote: > > <<<snip>>> > > > >Or if you don't have the ETS module but do have STAT module, then PROC > >STDIZE. > > > >Hope this is helpful, > > > >Dan > > Umm, Dan, I believe that PROC STANDARD is in Base SAS. So everyone > has it. > > Still, PROC STDIZE is a good tool to have in the toolbox. It does a lot > more than PROC STANDARD, and provides robust and resistant measures > of location and spread to do the normalization. > > HTCT, > David > -- > David L. Cassell > mathematical statistician > Design Pathways > 3115 NW Norwood Pl. > Corvallis OR 97330 > > _________________________________________________________________ > All-in-one security and maintenance for your PC. Get a free 90-day trial! > http://www.windowsonecare.com/trial.aspx?sc_cid=msn_hotmail David, You are correct (as is usually the case). Because I can never can remember which modules various procs are in I actually looked in the SAS help files. I not sure why I couldn't see PROC STANDARD in the list. Maybe the crowd noise still ringing in my ears from the Seahawks game was affecting my ability to process info clearly. :-) Dan Daniel J. Nordlund Research and Data Analysis Washington State Department of Social and Health Services Olympia, WA 98504-5204
|
Next
|
Last
Pages: 1 2 Prev: Converting Cobol PIC to SAS informats Next: Variable length when using Proc Import |