SPSS versus R

[Mehrshad Koleini]

Dear Sir/Madam

 

Hi. I have purchased SPSS 17.0, and now for some calculations I use R, too. I have planned to study some topics in advanced statistics. The issue is this, should I put my force on learning R, or SPSS? Is R satisfactory for advanced statistical analysis?

 

Kind regards

 

Mehrshad

[Bruce Weaver]

Here on the SPSS mailing list, a lot of people will (naturally) steer you towards SPSS.  If you post the same question on an R-list, you'll be told that without question R is superior (not only to SPSS, but to everything else as well).  Which one you focus on probably depends on the following, among other things:

1. How important will it be for you to update SPSS if you choose it, and can you afford those updates?  (Bear in mind the modular nature of SPSS when thinking about this one.)
2. What do you mean by "advanced" statistical analysis?  Please provide some examples.
3. Do you have colleagues you need to share work with?  If so, what do they use?
4. How much previous experience have you got with SPSS?  Are you a point-and-click user, or do you use syntax?  If you use syntax, what about macros or the matrix language?  
5. How comfortable have you been with what you've seen of R so far?  

HTH.

Mehrshad Koleini wrote

Dear Sir/Madam



Hi. I have purchased SPSS 17.0, and now for some calculations I use R, too.
I have planned to study some topics in advanced statistics. The issue is
this, should I put my force on learning R, or SPSS? Is R satisfactory for
advanced statistical analysis?



Kind regards



Mehrshad

[robert.heiser]

I'll chime in, as I'm in the process of moving my research from SPSS to
R, (and perhaps my research students as well). As an academic user, I've
found the SPSS menu structure makes statistical analysis easy--at least
for the initial first or second pass of analysis. The menu structure for
data analysis is  setup for relatively straight-forward point and click;
attributes which make teaching the program to business students less
complicated. In addition, SPSS technical and statistics support has
always been stellar for me.

On the downside, the changes in the output format for recent SPSS
versions, making them frustratingly incompatible with earlier research
output files (BTW, the free output reader does not work on my Win7
machines);  the additional charges for stat analysis procedures that
perhaps should be included in the already expensive base program price;
and the lack of a good "student version" (the Career Pack doesn't cut
it), together encouraged me to learn R this summer.

As for learning R, the programmer-like syntax creates a difficult
initial learning curve; however, once you get the hang of the program,
you can perform virtually any statistical procedure. In addition, most
stat researchers now create R programs for their new procedures, so
there is no lag between publishing a new procedure and trying it out on
your data. Finally, there are some R helper programs such as R Studio
which help you transition from a GUI statistical environment.

If you're looking for advanced analysis, R is the way to go with over
3000 stat packages available through CRAN and many more available at
authors' websites. However, as per normal "programming" environments, R
can sometimes be difficult to debug and run.

A few thoughts...

On 8/7/2011 9:26 AM, Bruce Weaver wrote:

> Here on the SPSS mailing list, a lot of people will (naturally) steer you
> towards SPSS.  If you post the same question on an R-list, you'll be told
> that without question R is superior (not only to SPSS, but to everything
> else as well).  Which one you focus on probably depends on the following,
> among other things:
>
> 1. How important will it be for you to update SPSS if you choose it, and can
> you afford those updates?  (Bear in mind the modular nature of SPSS when
> thinking about this one.)
> 2. What do you mean by "advanced" statistical analysis?  Please provide some
> examples.
> 3. Do you have colleagues you need to share work with?  If so, what do they
> use?
> 4. How much previous experience have you got with SPSS?  Are you a
> point-and-click user, or do you use syntax?  If you use syntax, what about
> macros or the matrix language?
> 5. How comfortable have you been with what you've seen of R so far?
>
> HTH.
>
>
>
> Mehrshad Koleini wrote:
>> Dear Sir/Madam
>>
>>
>>
>> Hi. I have purchased SPSS 17.0, and now for some calculations I use R,
>> too.
>> I have planned to study some topics in advanced statistics. The issue is
>> this, should I put my force on learning R, or SPSS? Is R satisfactory for
>> advanced statistical analysis?
>>
>>
>>
>> Kind regards
>>
>>
>>
>> Mehrshad
>>
>
> -----
> --
> Bruce Weaver
> [hidden email]
> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/SPSS-versus-R-tp4674768p4674980.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD

--
Bob Heiser, Ph.D.
Associate Professor of Marketing
School of Business, LB216
Box 9300, Portland, ME 04101
web: http://usm.maine.edu/~rheiser/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Rich Ulrich]

Think about the questions that Bruce asks.

Also - What are you doing?  Are you a student, just starting out?

In the world of data analysis - if you get raw data from various sources -
you can spend 90% of your time "cleaning data" before you do analyses;
and exploring and computing new scores.  And you will want to be able
to *document*  everything that you do.   I think that R users would agree
that a stat package is better for those things.

--
Rich Ulrich

---

Date: Sun, 7 Aug 2011 03:53:57 -0700
From: [hidden email]
Subject: SPSS versus R
To: [hidden email]

Dear Sir/Madam

 

Hi. I have purchased SPSS 17.0, and now for some calculations I use R, too. I have planned to study some topics in advanced statistics. The issue is this, should I put my force on learning R, or SPSS? Is R satisfactory for advanced statistical analysis?

 

Kind regards

 

Mehrshad