[RsR] Robust Anova with missing values

[Manuel Koller]

Dear Tom,

It's difficult to give concrete advice with this little information. But you might want to try to formulate your anova as mixed effects model and use robust mixed effects models instead. Unbalancedness and crossed factors are no problem at least with my package robustlmm. It builds on lme4 and has similar syntax. There is also the package heavyt that builds on nlme, you might want to check that out as well. 

Hope this helps,
Manuel

On 9. Oct 2013, at 23:17 , "Worthington, Thomas A" <thomas.worthington using okstate.edu> wrote:

> I am trying to run a robust anova  from the WRS package using either of the functions
> 
> t2way(2,4,data2)
> 
> or
> 
> pbad2way(2,4,data2,est=median)
> 
> data2 contains eight columns of data for the 2 x 4 design, however the numbers of items in each column varies and therefore the dataset contains NAs
> When I run the functions I get an error message which I assume is related to the columns having different lengths, is there an equivalent function that can incorporate this unbalanced design?
> 
> Best wishes
> 
> Tom
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-SIG-Robust using r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-robust