Hello I am analysing aboveground biomass data from revegetation testplots which
I constructed in a split-plot design using the function lme. For the
experiment, the three factors are amelioration (2 levels), fertilizer (2
levels) and treatment (7 levels). Each testplot (block) has a singlereplicate
of each treatment (total of 8 testplots). The blocks were constructed of
topsoil. Each block was divided in two subplots in which half were ameliorated
the other half was not (amelioration - yes or no). Each subplot was divided
again into two subplots (fertilizer - yes or no). Then for eachfertilizer
subplot, the area was divided into 7 seeding treatments (treatments). I have
transformed my data to meet model assumptions and simplified my model using
stepwise elimination. Here is my minimal model: fm13<-
lme(sqrt(abovegroundbiomass.m.2)~amelioration+fertilizer+treatment,random=~1|block,
method="ML",na.action = na.omit) Here is a summary output: summary(fm13)$tTable
Value Std.Error DF
t-value p-value
(Intercept) 1.6196612 0.9058574 100 1.7879869
7.680688e-02
ameliorationyes 1.0155789 0.5970789 100 1.7009125
9.206718e-02
fertilizeryes 4.3153841 0.5970789 100 7.2274943
9.985161e-11
treatmentelymgla ecovar 5.0125584 1.1170323 100 4.4873891
1.931291e-05
treatmentelymgla local 2.7699072 1.1170323 100 2.4797020
1.482059e-02
treatmentfestsax ecovar 0.6953266 1.1170323 100 0.6224768
5.350453e-01
treatmentlupiarc local 1.1391840 1.1170323 100 1.0198309
3.102696e-01
treatmentnativemix ecovar 2.1091683 1.1170323 100 1.8881892
6.189917e-02
treatmentnativemix local 3.2103166 1.1170323 100 2.8739694
4.951797e-03 I would like to obtain the back-transformed estimates but I cannot
seem to find the a way to do this. I have a copy of Crawley (The R Book) but
could not find instructions on how to back-transform in lme. I have also look
for a copy of Zuur (Mixed Effects Models and Extensions in Ecology with R) but
cannot seem to obtain a copy. Any guidance in how to backtranform these
estimates would be greatly appreciated. Thanks. Allan CarsonGraduate
StudentUniversity of Northern British Columbia
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
