PSPP – the free, open source version of SPSS

I just heard recently about PSPP, which is a free, open source version of SPSS.

I have not tried it yet, but it does look promising. This is the description from its website:

It is a Free replacement for the proprietary program SPSS, and appears very similar to it with a few exceptions.

The most important of these exceptions are, that there are no “time bombs”; your copy of PSPP will not “expire” or deliberately stop working in the future. Neither are there any artificial limits on the number of cases or variables which you can use. There are no additional packages to purchase in order to get “advanced” functions; all functionality that PSPP currently supports is in the core package.

PSPP can perform descriptive statistics, T-tests, linear regression and non-parametric tests. Its backend is designed to perform its analyses as fast as possible, regardless of the size of the input data. You can use PSPP with its graphical interface or the more traditional syntax commands.

Sounds pretty good, huh?

The only downside I can see, though, is with the statement “no additional packages to purchase in order to get ‘advanced’ functions.”  That appears to be because there aren’t any advanced functions.  PSPP seems to correspond only to SPSS base.  No Advanced Models, no Missing Values Analysis, no Complex Surveys.  That means you can do one-way ANOVA and regression, but not GLM, logisitic regression, factor analysis.

So if you are only using SPSS for basic statistics, or for teaching an intro class, this may be just what you need.  And perhaps if it takes off, as R has, we’ll see more advanced features soon.

If you’ve had any experience using PSPP, please tell me about it in a comment.  I’d love to hear how well it works.

 

Getting Started with SPSS
Karen will introduce you to how SPSS is set up, some hidden features to make it easier to use, and some practical tips.

Reader Interactions

Comments

  1. Kit says

    Does anyone know if PSPP will read SPSS analysis files? For example, can I add to an existing SPSS file using PSPP and then use PSPP for free going forward? Thanks

    • TAF Support says

      Hi Kit,

      Glancing at the PSPP F.A.Q. on GNU’s site, it looks like it will read .sav files.

      Can PSPP open encrypted .sav or .sps files? PSPP includes a tool, named pspp-convert, that can decrypt encrypted .sav or .sps files, given the password. Please read the PSPP manual or the pspp-convert manual, for details.

      -Jeremiah

  2. Stefan says

    Does anyone know if SPSS is GCP (good clinic practice) conform and can therefore be used for „proper“ research? Does it have an audit trail function to track changes done? Thanks a lot Stefan

  3. bala says

    hi

    i downloaded from the site stated by karen
    it works good no virus issues till now , but one draw back is there no more statistical option , for ex., if we taking Mean means only SD option is available default no standard error means option so on , besides its works good.

    Bala

  4. Sylvance says

    I learned PSPP the other day with excitement. I call myself a seasoned user of SPSS although there is always something new to learn about it. So I have come to get familiar with PSPP quite easily. So far, I like everything about it and I would recommend it because it is free!

    My quarrel with it is just one. I can’t get to edit the output as easily as I do with SPSS. I think this should be an urgent priority to the programmers. The idea of any analysis is to produce a report which can be presented in the most presentable way to the audience. Besides a couple of other features, SPSS is still quite the program to use (if you can afford it)

  5. mahboubeh says

    right now i am a starter in English course i have lots of problem with data analysis.
    is there any body here and would you mind doing me a favor and helping me .
    best
    Mahboubeh

  6. Alex says

    I am using PSPP for my last year in Psychology, and am finding the lack of advanced options limiting. Because SPSS cannot run on my computer (Linux), I am forced to use PSPP. It would be very handy if PSPP could include a factorial ANOVA analysis and other more advanced statistical analyses.
    However, for basis analyses, SPSS is fantastic!

    • Lukas says

      I have tried the above cloud service for PSPP, great for working from MAC as it is independent of the system. Thumbs up and thanks for the tip!

  7. Erik WInther Paisley says

    This is an old post, but in case you’re interested, I do believe PSPP does have PCA / factor analysis. Otherwise, the free spreadsheet tool for Linux, gnumeric, has it built-in natively.

    It’s worth noting, too, that PSPP doesn’t really like Windows. It’ll run, but some functions won’t work.

  8. George says

    I agree with the previous poster – I wouldn’t have taken long to have a quick look at the software.

    This aside I found it at the time of writing to be very limited on functions for what I am after – I need to analyse neuroscientific data, primarily using either univariate analysis or repeated measures with between subjects factors – the software only provides a one way ANOVA so is pretty useless to me. Hopefully these features will be developed as at the moment this is no way a replacement to SPSS. It has T-tests, but you can do these excel.

  9. Eugênio says

    Yeah! It is very interesting having free software such as pspp… Yes, it is quite similar to SPSS and Yes, there is some function missing.
    I think it is ok once the software is a GNU so it is colaborative product, than it is permanentely in construction.
    I hope (basic) functions like missing value analysis could be brought as soon as possible. Unfortunately I have no expertise to help… I’m only a user…

  10. Saad says

    I have experience of working at SPSS and PSPP both. You may not believe that in my MS/M.Phil level thesis at my university i used PSPP & SPSS and found results to be approximately same.
    According to me, PSPP is a great software and a service for humanity. Personally speaking, i simply love it for being FREE and equally reliable.

  11. S O says

    I was alarmed at your attempt to review a piece of software you admit to not having used. I mean no disrespect, nor am I defending the PSPP package, but your complaints completely ignore the purpose of the software (an SPSS clone with development driven by academic goals) and concentrate on terminology borrowed from a commercial product (which PSPP is not).

    In short, if you know someone who is a capable programmer and would like to implement the features you see missing, ask if they are interested in contributing to PSPP. If you must use a feature not available, ask the developers how much work it would take, perhaps the cost of a single seat license of Complex Survey design would pay for the functionality to be developed and allow everyone access.

    • Karen says

      Hi SO,

      Fair enough. My intent was certainly not a review nor a complaint. I think it’s amazing that PSPP exists and I am hoping to get the word out and encourage more development. I certainly see why you responded as you did, though.

      I like your idea, though, of hiring a programmer for the price of an add-od module. Know any?

  12. Lynn says

    Does anyone know if PSPP results are reliable? I’m wondering what the previous poster meant by “the results are basically the same”. Also, does anyone know if people are starting to widely publish with PSPP?

  13. Mark says

    I have been working with SPSS and PSPP, the results are basically the same. PSPP just still misses some functions. However currently pspp added factor analysis and reliability analysis. I prefer using pspp because it is free (open source!!) software and is much faster than spss.

  14. Annie says

    Hi,

    I’m currently comparing these two software-packs. I think there might be a virus risk with downloading a free software from internet, don’t you?

    • Karen says

      Hi Annie,

      I think you’re safe if you download them from a reputable source. Both the links I gave are reputable, to the best of my knowledge.

      Karen


Leave a Reply

Your email address will not be published. Required fields are marked *

Please note that, due to the large number of comments submitted, any questions on problems related to a personal study/project will not be answered. We suggest joining Statistically Speaking, where you have access to a private forum and more resources 24/7.