How to set the nlme() function to return the answer without the intercept
parametrization?
#=========================================================================================
library(nlme)
Soybean[1:3, ]
(fm1Soy.lis <- nlsList(weight ~ SSlogis(Time, Asym, xmid, scal),
data = Soybean))
(fm1Soy.nlme <- nlme(fm1Soy.lis))
fm2Soy.nlme <- update(fm1Soy.nlme, weights = varPower())
plot(ranef(fm2Soy.nlme, augFrame = TRUE),
form = ~ Year * Variety, layout = c(3,1))
soyFix <- fixef(fm2Soy.nlme)
options(contrasts = c("contr.treatment", "contr.poly"))
(fm3Soy.nlme <-
update(fm2Soy.nlme,
fixed = Asym + xmid + scal ~ Year,
start = c(soyFix[1], 0, 0, soyFix[2], 0, 0, soyFix[3], 0, 0)))
# here I wouldn't like give the intercept parametrization but
# the parameters by tratament with standard error. See:
# before:
# Fixed effects: list(Asym ~ Year * Variety, xmid ~ Year + Variety, scal - 1
~ Year)
# Value Std.Error DF t-value p-value
# Asym.(Intercept) 19.43400 0.9537402 352 20.37661 0.0000
# Asym.Year1989 -8.84208 1.0721164 352 -8.24731 0.0000
# Asym.Year1990 -3.70719 1.1770024 352 -3.14969 0.0018
# after (I would like this):
# Fixed effects: list(Asym ~ Year * Variety, xmid ~ Year + Variety, scal - 1
~ Year)
# Value Std.Error DF t-value p-value
# Asym.Year1988 19.43400 0.9537402 352 20.37661 0.0000
# Asym.Year1989 -8.84208 1.0721164 352 -8.24731 0.0000
# Asym.Year1990 -3.70719 1.1770024 352 -3.14969 0.0018
#=========================================================================================
Thanks in advance.
Fábio Mathias Corrêa UFLA
Veja quais são os assuntos do momento no Yahoo! +Buscados
[[alternative HTML version deleted]]
______________________________________________
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel
