-Except 4 sites (S1,S4, L1,I1) with missing data for early sampling. The following 3 plots are just different flavours of the same graph:
From here on, plots show a smooth conditional mean with standard error:
(except S1 &S4)
(except L1)
(except I1. Same legend as above graphs)
(both leaflitter types. From here on, removed Std.error to see slopes better)
##…Next steps, model exploration: Note: Very general model using Time as continuous variable and including Day0=>Final.mass=2g
M1 <- lme(log(Final.mass) ~ Days*Size.new*Leaves, data=deczero, random = ~1|Site,method="ML")
plot(M1)
anova(M1,test="Chisq")
## numDF denDF F-value p-value
## (Intercept) 1 594 8418.048 <.0001
## Days 1 594 1618.706 <.0001
## Size.new 2 16 1.163 0.3376
## Leaves 1 594 53.715 <.0001
## Days:Size.new 2 594 1.209 0.2993
## Days:Leaves 1 594 53.657 <.0001
## Size.new:Leaves 2 594 0.109 0.8964
## Days:Size.new:Leaves 2 594 0.735 0.4798