R help - Nov 2011 - Non parametric, repeated-measures, factorial ANOVA

Hi

I have data from an experiment that used a repeated-measures factorial 2x2
design (i.e. each participant contributed data to both levels of both
factors). I need a non-parametric version of the repeated-measures factorial
ANOVA to analyse the data. SPSS only has non-parametric tests for one-way
ANOVAs but I have been told that the test I need can be implemented using
the R software.

Unfortunantly I haven't been able to work out how to do this test in R.
I've
got the Wilcox book 'Robust Estimation and Hypothesis testing' but to be
honest I don't have enough of a background in stats to understand a great
deal of it, and I wasn't able to work out how to do the test I want. Can
anyone let me know how I can do such a test in R? I presume this is a test
that people frequently need to use and that there will be some code already
written that can implement the test.

Thanks
Rob

--
View this message in context:
http://r.789695.n4.nabble.com/Non-parametric-repeated-measures-factorial-ANOVA-tp4118816p4118816.html
Sent from the R help mailing list archive at Nabble.com.

On 11/29/2011 10:31 PM, RobH2011 wrote:
> Hi
>
> I have data from an experiment that used a repeated-measures factorial 2x2
> design (i.e. each participant contributed data to both levels of both
> factors). I need a non-parametric version of the repeated-measures
factorial
> ANOVA to analyse the data. SPSS only has non-parametric tests for one-way
> ANOVAs but I have been told that the test I need can be implemented using
> the R software.
>
> Unfortunantly I haven't been able to work out how to do this test in R.
I've
> got the Wilcox book 'Robust Estimation and Hypothesis testing' but
to be
> honest I don't have enough of a background in stats to understand a
great
> deal of it, and I wasn't able to work out how to do the test I want.
Can
> anyone let me know how I can do such a test in R? I presume this is a test
> that people frequently need to use and that there will be some code already
> written that can implement the test.
Hi Rob,
The nparLD package, based on the work of Professor Brunner, might do 
what you want.

Jim

Hi

Thanks for your reply. The package appears to be for the analysis of
longitudinal designs, and requires a time factor to be input on the relevant
. My experiment is just a standard repeated-measures design, and I just need
a direct, non-parametricc equivalent of the Factorial repeated-measures
ANOVA.

It occurs to me that the terminology I am using might be a problem - when I
say repeated measures I mean that it is a within subjects design, so that
each subject does each condition, counterbalanced so that order/time effects
are not an issue.

Thanks
Rob

--
View this message in context:
http://r.789695.n4.nabble.com/Non-parametric-repeated-measures-factorial-ANOVA-tp4118816p4122501.html
Sent from the R help mailing list archive at Nabble.com.