My data are (for one experiment):
3 Types of plant (1,2,3)
4 Species per Type (ex:for type 1(a,b,c,d), for type 2(e,f,g,h) and
for type 3(i,j,k,l)
8 Repetitions of each Species
3 Stages (10, 20, 30)
2 Measures per Stages, for the stages 20 and 30 (ex: for Stage 10(C),
for Stage 20 (A and B) and for Stage 30 (A and B)
3 Types x 4 Species(Type) x 8 Repetitions x (1 Stage x 1 Mesure + 2
Stages x 2 Measures= 480 data. There are 10 data missing. The final
number of data is 470.
My questions that I ask to my data:
1- Is there a significant difference between Measure A and Measure B?
2- Is there a significant difference between Stages 10, 20 and 30?
3- Is there a significant difference between the 3 plant Types?
I haven't found any way to consider the whole data lot in one shot, I
decided to remove the first stage with the Measure "C" that comes
with
it. It bring the number of data to 384.
Is it possible to consider the whole lot in one shot?
Thus my model is
Source d.l.
Types 2
Species (Type) 9
Error a) 84
Stage 1
Measure 1
Stage x Measure 1
Stage x Type 2
Measure x Type 2
Stage x Measure x Type 2
Stage x Species (Type) 9
Measure x Species (Type) 9
Stage x Measure x Species (Type) 9
Erreur b) 252
Total 383
How can I write this in R? My problem is that when I use %in% to nest
Species in Type, R looks, for exemple, for specie "a" in Type 2 and
it
finds nothing and returns "Na".
Type1:Plante[T.a] -1.51967 0.82774 -1.836 0.0672 .
Type2:Plante[T.a] NA NA NA NA
Can you help me? Can R consider Species a,b,c,d only in Type 1,
Species e,f,g,h only in Type 2 and Species i,j,k,l only in Type 3?
Thank you very much.
