P.Mean: Which version of SPSS should you get (created 2011-06-03).

News: Sign up for "The Monthly Mean," the newsletter that dares to call itself average, www.pmean.com/news.

I was showing a client how to use their version of SPSS to a variety of different things and when I went to run a logistic regression model, it wasn't there. Apparently, there are several versions of SPSS (I knew this already) and some of the versions do not include logistic regression (that I was surprised to find out). I had to research all the options and offer a recommendation. Here's a quick guide to what I learned by browsing through the SPSS site.

As a general rule, SPSS comes in small, medium, large, and extra large versions, and you can add specific modules to any of those versions.

The small version of SPSS is called IBM SPSS Base Statistics package.
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/base/

It has fairly minimal capabilities. In my opinion, if you're going to take the plunge and spend the sort of money that SPSS is asking for, you don't want such a limited version.

The medium version of SPSS is called IBM SPSS Statistics Standard Edition
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/stats-standard/

This is the version that includes logistic regression. It also has the generalized linear model, generalized linear mixed model, and generalized estimating equations. If you are doing more than just baby statistics, you will eventually need some of the capabilities in these models.

The large version of SPSS is called IBM SPSS Statistics Professional Edition
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/stats-pro/

The best addition to this package is the missing values analysis module. Other stuff, like the decision trees, are overrated.

The extra large version of SPSS is called IBM SPSS Statistics Premium Edition
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/stats-premium/

It provides bootstrapping (a very powerful but greatly under utilized tool), and structural equations modeling (nice, but kind of a niche product).

There are specialized modules which you can get that may or may not already be included in the package you have. Some of the more interesting modules are:
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/complex-samples
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/exact-tests
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/forecasting
 * http://www-01.ibm.com/software/analytics/spss/products/statistics/neural-networks

If you know the specialized procedures you will need, then you can buy just those procedures. The problem is that data analysis takes unexpected turns, so it may make sense to plan for growth into new and more advanced areas of SPSS. Here's my opinion for what it's worth. SPSS Statistics Standard Edition is a nice package for the money. It gives you enough capabilities that you can grow into many of the types of analyses you might need. If you are a serious hard core data analyst, then you go for extra large, the premium edition. You don't get enough from the large version, the professional edition, to justify the increase in cost. I won't go into the SAS versus SPSS debate, but if you are hard core (and have a big enough budget), you should take a look at and compare all your options, and SAS is a serious alternative to SPSS.

This will change, of course, as new versions come out and you should talk to your SPSS sales representative rather than trust what I am saying.

Creative Commons License This page was written by Steve Simon and is licensed under the Creative Commons Attribution 3.0 United States License. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Spss Software.