[R] Error when using cobs library

[Martin Maechler]

>>>>> "Martin" == Martin Maechler <maechler at stat.math.ethz.ch>
>>>>>     on Sat, 4 Nov 2006 10:59:16 +0100 writes:

>>>>> "jacinthe" == jacinthe  <jacinthe at gmx.de>
>>>>>     on Sat, 04 Nov 2006 10:06:10 +0100 writes:

    jacinthe> Dear R-Users, I have problems with the cobs
    jacinthe> library.
    Martin> ^^^^^^^
    Martin> It's package!
    Martin> It's package!
    Martin> .............
    Martin> [say it load five times, so you re-train your brain ]
		    ^^^^
to which Peter Dalgaard  appropriately responded

  PD>   It's loud!
  PD>   It's loud!
  PD>   ...
  PD> 
  PD>    ;-)


    jacinthe> When doing the cobs example, I get the
    jacinthe> folling error message:

    [................]

    Martin> Of course, the above works "typically", since otherwise the
    Martin> package would not be on CRAN.

    jacinthe> Any suggestions how to fix this problem?

    Martin> It's not easy to help you, since you didn't give any details
    Martin> about your setup.
    Martin> Please do so, e.g. by showing the result of sessionInfo().

In the mean time "jacinthe" sent me

    Jaci> sessionInfo()
    Jaci> Version 2.3.1 (2006-06-01) 
    Jaci> i386-pc-mingw32 

    Jaci> attached base packages:
    Jaci> [1] "splines"   "methods"   "stats"     "graphics"  "grDevices" "utils"     "datasets"  "base"     

    Jaci> other attached packages:
    Jaci> cobs       quantreg     SparseM   fMultivar  fSeries  .....
    Jaci> "1.1-3.5"    "4.01"      "0.68" "221.10065" "221.10065" ......


which I think explains things:

Your version of SparseM is probably too old and or may not have
been for R 2.3.1.

Do the following

1) Get R 2.4.0 (or even R-2.4.0-patched)

2) upgrade.packages()

   where you should get newer versions of SparseM (and quantreg)

[you can also try to do "2)" alone; and that will be much quicker;
 but note that S4 class/methods handling has been wastly
 improved for R 2.4.0 and later, and SparseM does use them]



    Martin> I guess a mismatch of versions of the packages involved,
    Martin> notably your version of "SparseM" maybe outdated.

    jacinthe> Thank you for your help.

    Martin> you're welcome.
    Martin> Martin Maechler, ETH Zurich