Non Parametric alternative to a Mixed Measures ANOVA

Hi All,

I am wondering if you can help me out with a problem i am having.

Firstly, i have a single between subjects IV (gender) and then two within subjects IVs (1) Decision type with 4 levels and (2) Time pressure with 2 levels (high and low). The single DV is accuracy. Therefore, i have a mixed related and independent factors.

Secondly, i don't have a normal distribution and due to the sample size it isn't appropriate to use a parametric test.

Thirdly, participants got to choose their decision type (repeated IV1) - that is they did not have to complete all 4 levels of this IV, they just needed to choose 1 decision type to use in the high time pressure and 1 decision type in the low time pressure (repeated IV2). Therfore, i don't have equal numbers of results under each of my "Decision Type" levels - some decision types were chosen by many participants, others by only a few. Therefore, i end up excluding nearly all data list-wise with many of the stats procedures.

HELP HELP HELP. In summary the title of this post says it all. I (think) i need a non-parametric, mixed measures ANOVA (that doesn't have a problem with missing data)!

Thank you so much!
To my knowledge, there is no nonparametric equivalent to mixed anova.

At best, I'm pretty sure in simpler models it is considered legitimate to convert all the data to ranks and run an ANOVA. I believe that the results for this are similar to running a rank-based test (such as a kruskall-wallis). I don't know if this still applies once you're trying to incorporate interactions.

A few other remarks, though. Are you sure you need to abandon parametrics? What is the non-normal distribution? How small are your samples?

And it sounds like your missing data problem may just be that Time Pressure and Decision Type are not crossed. You may be able to include both in the model, just not their interaction. If you're running it in a Mixed Modeling procedure (with data in the long format) rather than a Repeated Measures procedure (with data in the wide format), it should be less of a problem.

And if you're not following what I'm talking about, let me know and I'll clarify. :)