Dear all
A colleague that does not have access to this list asked me to post this
message:
> When fitting a lme model for an incomplete and unbalanced design
>
> > lme(dur~sp, data=clara, random=~1|sp/indiv)
>
> the following error message appears
>
> Error in if (any(wchLv <- (as.double(levels(xtTab[, wchPval])) == 0))) {
> :
> missing value where logical needed
> In addition: Warning message:
> NaNs produced in: pt(q, df, lower.tail, log.p)
>
> The number of observations is different for each cell and there is a
> different number of levels of factor "indiv" for each level of
factor
> "sp". Is this error due to the characteristics of the data set or
am i
> doing something wrong? I used nlme 3.1-19 and R 1.4.1.
> Thanks in advance
>
> Clara
>
> Full summary() output is below:
>
> > summary(lme(dur~sp, data=clara, random=~1|sp/indiv))
> Linear mixed-effects model fit by REML
> Data: clara
> AIC BIC logLik
> 3628.559 3649.493 -1808.279
>
> Random effects:
> Formula: ~1 | sp
> (Intercept)
> StdDev: 120.1199
>
> Formula: ~1 | indiv %in% sp
> (Intercept) Residual
> StdDev: 95.65147 407.0695
>
> Fixed effects: dur ~ sp
> Error in if (any(wchLv <- (as.double(levels(xtTab[, wchPval])) == 0))) {
> :
> missing value where logical needed
> In addition: Warning message:
> NaNs produced in: pt(q, df, lower.tail, log.p)
--
Alberto G. Murta
IPIMAR - Institute of Fisheries and Sea Research
Avenida de Brasilia, 1449-006 Lisboa, Portugal
Tel:+351 213027062; Fax:+351 213015849; http://www.ipimar.pt/pelagicos/
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._