[R] again evaluations

Martin Maechler maechler at stat.math.ethz.ch
Thu Dec 13 18:50:25 CET 2001

>>>>> "Heberto" == Heberto Ghezzo <heberto.ghezzo at mcgill.ca> writes:

    Heberto> Hello, I wrote the following function to compute
    Heberto> multiple comparisons in a one way anova and
    Heberto> randomized blocks anova.

    Heberto> aov1 <-
    Heberto>   function(y,g,s=NULL,comp="mca",meth="Sidak") { #
    Heberto> b <- multicmp(a[1,],a[3,],sig,df.residual=df,method=meth)

    Heberto> If I call "aov1(x,g)" everything
    Heberto> works as expected but with "aov1(x,g,s=s)" or
    Heberto> "aov1(x,g,s)" I get the error

    Heberto> Error in eval(expr, envir, enclos) : Object "y" not
    Heberto> found

we have no real chance of reproducing your problem.
you use `data' -- your "x" and "g" and "s" that we don't have
available and you use a function multicmp() which is not part of R
(which might be not called before the error though).

after the error message would help potentially.

    Heberto> I am using R 1.3.1 on Win98. Can somebody explain
    Heberto> why adding a parameter makes the first parameter
    Heberto> invisible?  Thanks

well, it's a different model you are fitting,...

maybe you could use a data frame to pass to  aov(*, data = <data frame>)

    Heberto> Heberto Ghezzo Meakins-Christie Labs McGill
    Heberto> University Montreal - Canada
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

More information about the R-help mailing list