[R] errores

[Douglas Bates]

>>>>> "PBM" == Peter B Mandeville <mandevip at 148.224.17.2> writes:

  PBM> 	2. The following code on page 312 of Venables and Ripley 1997

  PBM> sitka.lme <-
  PBM> lme(size~treat*ordered(Time),random=~1,cluster=~tree,data=Sitka,
  PBM> serial.structure="ar1.continuous",serial.covariate=~Time)

  PBM> produced the following error message

  PBM> Error in lme(size ~ treat * ordered(Time), random = ~1, cluster
  PBM> = ~tree, : unused argument to function

  PBM> The example listed on the help for LME worked without problem.

  PBM> I don't know if my last error reports got out of Mexico or not
  PBM> so here they are again.

The version of the lme library in R is a beta version of nlme 3.0.
The version that is documented in Venables and Ripley (1997) is version
2.1, the only version that was available at the time they wrote the
book.

Jose' Pinheiro and I have made incompatible changes in the calling
sequence of lme between the two versions of the nlme library.  We did
this because we felt the current version is much easier to use and to
understand.  The corresponding call in the current version would be

sitka.lme <-
 lme(size ~ treat*ordered(Time), data = Sitka, random = ~ 1 | tree,
     correlation = corCAR1(form = ~ Time))

This is still going to produce a massive number of coefficients from
the ordered(Time) term.

By the way, it would help if you had your system administration
reconfigure your mailer so it provides a system name in the From: line
rather than an IP address.
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._