[RsR] 'ROptRegTS' load error

Johannes Graumann joh@nne@_gr@um@nn @end|ng |rom web@de
Wed Nov 26 20:49:47 CET 2008


Yes, fresh R session (see below). Whether it's working? I was looking for a 
function straight forward to use - along the lines of "roblox" - but failed. 
Can you give a hint on how to actually set up something mimicking 

library(robustbase)
(regression <- lmrob(
  y~x
))

I have had very good results using "roblox" in the past and was interested in 
trying the regression based on the same methodology, but being a user and no 
specialist the package has me intimidated.

Joh


> sessionInfo()
R version 2.8.0 (2008-10-20) 
x86_64-pc-linux-gnu 

locale:
LC_CTYPE=en_US.UTF-8; <CUT>

attached base packages:
 [1] stats4    tcltk     tools     stats     graphics  grDevices utils    
 [8] datasets  methods   base     

other attached packages:
 [1] ROptRegTS_0.6.0        distrMod_2.0.2         MASS_7.2-44           
 [4] ROptEst_0.5.0          RandVar_0.6.5          distrEx_2.0.2         
 [7] evd_2.2-4              distr_2.0.2            SweaveListingUtils_0.1
[10] sfsmisc_1.0-6          startupmsg_0.5.2       robustbase_0.4-3      
[13] RColorBrewer_1.0-2     geneplotter_1.20.0     annotate_1.20.1       
[16] xtable_1.5-4           lattice_0.17-17        MaxQuantUtils_1.17    
[19] tkrplot_0.0-18         TeachingDemos_2.3      plotrix_2.5           
[22] gsubfn_0.3-7           proto_0.3-8            AnnotationDbi_1.3.12  
[25] RSQLite_0.7-1          DBI_0.2-4              Biobase_2.1.7         
[28] rkward_0.4.9          

loaded via a namespace (and not attached):
[1] grid_2.8.0         KernSmooth_2.22-22 RobAStBase_0.1.2  

On Wednesday 26 November 2008 19:32:47 Matthias Kohl wrote:
> Dear Joh,
>
> was this a fresh R session?
>
> I just removed version 0.6 of package ROptEst and let the rest of the
> packages unchanged. Then, installed version 0.5 of ROptEst and after
> that installed version 0.5 of package ROptRegTS (from CRAN). Despite
> some warnings and notes during installation, all seems to work fine ...
>
> Does ROptRegTS work on your system?
>
> Best,
> Matthias
>
> Johannes Graumann wrote:
> > ROptEst 0.5! Not ROptRegTS! Sorry.
> >
> > Joh
> >
> > Johannes Graumann wrote:
> >> Hello Matthias,
> >>
> >> ROptRegTS 0.5 installs fine on top of the most recent rest of the bundle
> >> from R-Forge. When loading it I get the warnings below. Whether the
> >> functionality is impeded will be figured out later today.
> >>
> >> Thanks for your help!
> >>
> >> Joh
> >>
> >>> warnings()
> >>
> >> Warning messages:
> >> 1: In fun(...) ... : no valid postscript previewer found; consider
> >> setting options("eps_view"=  "....")	    yourself
> >> 2: Multiple methods tables found for 'optIC'
> >> 3: Multiple methods tables found for 'neighbor<-'
> >> 4: Multiple methods tables found for 'CallL2Fam<-'
> >> 5: Multiple methods tables found for 'generateIC'
> >> 6: Multiple methods tables found for 'checkIC'
> >> 7: Multiple methods tables found for 'clip'
> >> 8: Multiple methods tables found for 'clip<-'
> >> 9: Multiple methods tables found for 'cent'
> >> 10: Multiple methods tables found for 'cent<-'
> >> 11: Multiple methods tables found for 'stand'
> >> 12: Multiple methods tables found for 'stand<-'
> >> 13: Multiple methods tables found for 'lowerCase'
> >> 14: Multiple methods tables found for 'lowerCase<-'
> >> 15: Multiple methods tables found for 'neighborRadius'
> >> 16: Multiple methods tables found for 'neighborRadius<-'
> >> 17: Multiple methods tables found for 'clipLo'
> >> 18: Multiple methods tables found for 'clipLo<-'
> >> 19: Multiple methods tables found for 'clipUp'
> >> 20: Multiple methods tables found for 'clipUp<-'
> >> 21: Multiple methods tables found for 'L2deriv'
> >> 22: Multiple methods tables found for 'FisherInfo'
> >> 23: Multiple methods tables found for 'checkL2deriv'
> >>
> >> Matthias Kohl wrote:
> >>> Dear Joh,
> >>>
> >>> we are currently restructuring and extending our packages.
> >>>
> >>> Some parts of the package ROptEst (version 0.5) are now included in the
> >>> new packages distrMod and RobAStBase. Unfortunatelly, the structure of
> >>> the packages ROptRegTS and RobRex has not been updated yet. Hence, if
> >>> you want to use package ROptRegTS you have to use the old version
> >>> (i.e., version 0.5) of ROptEst from the archive
> >>> (http://cran.at.r-project.org/src/contrib/Archive/ROptEst).
> >>>
> >>> These old versions of the packages ROptEst and ROptRegTS should work
> >>> with R 2.8.0 and the recent versions of the packages distr, distrEx and
> >>> RandVar. I will check this later today and will then give you more
> >>> details on this.
> >>>
> >>> Best
> >>> Matthias
> >>>
> >>> Johannes Graumann wrote:
> >>>> Hello,
> >>>>
> >>>> Trying to say "library(ROptRegTS)", I get the error below. Can anyone
> >>>> help me pinpoint what's wrong?
> >>>>
> >>>> Thanks, Joh
> >>>>
> >>>> Error in loadNamespace(package, c(which.lib.loc, lib.loc), keep.source
> >>>> = keep.source) :
> >>>>   in 'ROptRegTS' methods for export not found: neighbor, bound, Curve,
> >>>>   CallL2Fam
> >>>> In addition: Warning message:
> >>>> In fun(...) : no valid postscript previewer found; consider setting
> >>>>   options("eps_view"=  "....")	    yourself
> >>>> Error: package/namespace load failed for 'ROptRegTS'
> >>>>
> >>>> _______________________________________________
> >>>> R-SIG-Robust using r-project.org mailing list
> >>>> https://stat.ethz.ch/mailman/listinfo/r-sig-robust
> >
> > _______________________________________________
> > R-SIG-Robust using r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-sig-robust


-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 835 bytes
Desc: This is a digitally signed message part.
URL: <https://stat.ethz.ch/pipermail/r-sig-robust/attachments/20081126/f9e2ee44/attachment.sig>


More information about the R-SIG-Robust mailing list