JASP might finally be the SPSS replacement we’ve been waiting for

i-don-t-always-make-shity-tables-and-figures-from-my-data-but-whI use SPSS for statistical analysis, but I don’t like it. Every time I do, I feel like the victim in some kind of emotionally abusive relationship. The interface is deeply horrid, the outputs are butt-ugly, and it runs like a three-legged overweight sloth with a heavy suitcase. It’s an absolute bloated dog of an application, and IBM clearly don’t give a crap about it, other than making some cosmetic updates every now and again. Plus the licensing system is bat-shit insane, and very expensive.

So, why do I keep using it? Because a) It’s what I learned as an undergraduate/PhD student and I know it backwards, and b) there are few viable alternatives. Yes, I know I should learn R, but I actually don’t use ‘normal’ stats that often (I spend most of my analysis time in brain-imaging packages these days) and every time I learn how to do something in R, I try doing it again a month later, have forgotten it, and have to learn it all over again. At some point I hope to become an R master, but for occasional use, I find the learning curve to be too steep. I would also hesitate to try and use R to teach students; I find it generally pretty user-hostile.

So, for ages now, I’ve been looking for a good, user-friendly, open-source alternative to SPSS. One that isn’t a bloated monster, but has enough features to enable basic analyses. I was quite hopeful about PSPP for a while (free software that tries to replicate SPSS as closely as possible). However it lacks some relatively basic ANOVA features, and since one of the things I dislike about SPSS is the interface, trying to replicate it seems like a bit of a mistake. SOFA statistics was a contender too, and it does have a beautiful interface and produce very nice-looking results, but it only does one-way ANOVAS, so… fail.

So, I gave up and crawled miserably back to SPSS. However, fresh hope now burns within my chest, as the other day I came across JASP (which the developers insist, definitely does not stand for ‘Just Another Statistics Program’). The aim of JASP is to be ‘a low fat alternative to SPSS, a delicious alternative to R.’ Nice. It seems to cover all the analysis essentials (t-test, ANOVA, regression, correlation) plus also has some fancier Bayesian alternatives and a basic Structural Equation Modelling option. The interface is great, and the results tables update in real-time as you change the options in your analysis! Very nice. This demo video gives a good overview of the features and workflow:

It’s clearly very much a work-in-progress. One issue is that it doesn’t have any in-built tools for data manipulation. It will read .csv text files, but they basically have to be in a totally ready-to-analyse format, which means general data-cleaning/munging procedures have to be done in Excel/Matlab/R/whatever. Another major downside is that there appears to be no facility for saving or scripting analysis pipelines. Hopefully though, development will continue and other features will gradually appear… I’ll be keeping a close eye on it!

Advertisements

About Matt Wall

I do brains. BRAINZZZZ.

Posted on November 27, 2014, in Commentary, Software, Study Skills and tagged , , , , , , , . Bookmark the permalink. 12 Comments.

  1. Thank you for the write-up – I’ve been looking at JASP since your tweet the other day. The features described look excellent, especially as I already do all all my data manipulation in SAS before I get to SPSS, so pointing a new application at a CSV file wouldn’t be too bad at all.

    I was interested to see that SAS isn’t on your list of loved/hated packages – is it one you’ve looked at? I use it for my day-job which is mainly data manipulation and presentation of frequency data rather than analysis.

    • Honestly I’ve never used SAS, and I don’t really see it being commonly used by colleagues, so I’ve never really paid it too much attention – I’ve been focussed on trying to find a free/open-source replacement really, so haven’t really considered SAS.

      • *nods* Fair enough. A lot of places seem to be either SAS or SPSS – I’m an odd hybrid in using both, I think 🙂 I’ll keep playing with JASP. Thanks again for the recommendation.

  2. Can you copy/paste in your data rather than import with as a .csv? I’m used to copy/pasting with GraphPad and it might be faster than setting up the .csv for some of my data sets.

  3. It looks great! I’ll give it a try.
    Thanks for sharing!
    Congratulations for your blog. Very useful.

  4. This is very useful if you just want to run an ANOVA and don’t want to install much. I haven’t tried it recently (no admin rights at work….) but did about 18months ago again when I was getting frustrated with SPSS licensing abroad, couldn’t face installing R, and wanted to check a student’s results and it worked FINE. Also quite good for forcing you/ a student to think about your design / contrasts.

    http://www.psy.unsw.edu.au/research/research-tools/psy-statistical-program

  5. Hi,
    Thanks for the post I was totally unmotivated with R, I couldn’t get into it. I will give JASP a try but from what I saw I really like it.

    thanks for the blogs is always nice to read it.

    cheers,
    George

  6. I have to maintain the SPSS here in our Psychology department, and each year I have a brief panic period where everyone realises their licences are coming to an end and they need another years fix. I ended up discussing the issue with the director of studies who was also the person charged with teaching undergraduates statistics. He felt that R was ready to go mainstream as there was now a good ‘how-to’ book for users (I don’t recall the details of the book I’m afraid). I avoided statistics like the plague, so I can’t comment on which is best, but R is popular with bioinformaticians, and the extensible nature of it through CRAN, inspired as it is by CPAN (Perl repositories) and CTAN (TeX repositories) makes it a winner in my mind.

  7. I actually like SPSS’s gui (and that’s probably the only reason I use SPSS as opposed to something lie R). What I don’t like is the constant state of disrepair of SPSS graphing capability (i.e., https://developer.ibm.com/answers/questions/243677/corrupted-chart-settings-when-an-output-file-is-sa.html ). JASP does appear to work! But apparently JASP’s graphs can’t be edited and can’t be exported as high resolution images. So JASP shows promise, but I still need SPSS graphing features despite the fact it (SPSS’s graphics) functions like an alpha or beta product.

  8. I have SPSS but have also been looking for a free program that would work for my students. I have spent enough time trying to learn R to know for a fact that it will not be an option for them. I will take a look at JASP in the next couple of days. Have you looked at the free version of MaxStat (i.e, MaxStat Lite)? It may be useful. I have also played around with PAST which has some nice features and may be worth a look.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: