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 (February 2004, week 1)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Thu, 5 Feb 2004 11:11:35 -0500
Reply-To:   Quentin McMullen <quentin_mcmullen@BROWN.EDU>
Sender:   "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:   Quentin McMullen <quentin_mcmullen@BROWN.EDU>
Subject:   Re: SPSS vs. SAS, redux
Comments:   To: Talbot Michael Katz <topkatz@MSN.COM>

Hi,

It's been a while for me since using SPSS, but a few thoughts:

On Wed, 4 Feb 2004 23:25:30 -0500, Talbot Michael Katz <topkatz@MSN.COM> wrote:

>(By the way, does SPSS have a list-serve comparable to SAS-L? Or >user groups like SUGI?)

Yes, there's an SPSS listserve, also hosted at UGA: http://listserv.uga.edu/archives/spssx-l.html

Maybe that SAS-L BOF should include not only a discussion of SAS-L stats, but whether or not we're beating SPSSX-L? One notable difference is that SPSS staff (tech support and statisticians) do participate in SPSSX-L

>Is "multiple missing data declaration, etc." anything comparable to PROC MI?

SPSS allows you to create "user defined missing values" for variables. So for sex you can define 8=missing 9=refused and for age you can define 888=missing 999=refused and for income you can define 88888888=missing 99999999=refused. Thanks, but no thanks. It's too messy, and doesn't work with date values. SAS special missing values (.M .R) are much better in my book.

>One of the things you often hear is that SPSS is easier to use than SAS, >that it's more point-and-click oriented.

That is certainly my sense (again may be outdated). I haven't looked at enterprise guide at all. Since learning SPSS (right after college) then making the move to SAS, I've come to think that SPSS is often *too* friendly. You open a dataset, and it opens like a spreadsheet. They try to hide the programming interface from you unless you look for it. And yes you can click-and-point your way through lots of analysis/data modification (and never have code! never be able to reproduce your results! : ), certainly easier than the old SAS/ANALYST. So you have some folks calling themselves "data managers" who are using SPSS in scary ways. It's easy to think that using SPSS is like using Excel.

Of course I don't mean to start an SPSS v. SAS battle. I'm sure there are many excellent programmers using SPSS in responsible ways. And in fact seems like SAS is putting lots of effort into the click-and-point analysis (I think folks said SAS LE also hides the program editor from you by default). I've only been to a handful of SUGI's, but I can't remember one opening session where someone said "well, let's open up some code in the editor, hit submit, and..."

Kind Regards, --Quentin


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