[R] How to enter partial hierarchical model in lme()

[Matthias Unterhuber]

I would need some help regarding a partial hierarchical model for anova.
Can anyone help me check whether the model is correct and what I should
enter in lme()?

My research design is (demonstrated for 4 subjects/Blocks):

      |     d1    |     d2    |
      |  a1 | a2  |  a1 | a2  |
      |b1|b2|b1|b2|b1|b2|b1|b2|   
Block1| x| x|  |  |  |  |  |  |
Block2|  |  | x| x|  |  |  |  |
Block3|  |  |  |  | x| x|  |  |
Block4|  |  |  |  |  |  | x| x|

Altogether there 92 subjects (about equal number for each condition)

A: random effect
B: random effect
Block: random effect
D: fixed effect


My analyis:

A and D are nested in Block, but A is not nested in D, and D is not nested
in A.

The model I propose is:


X~mu+A%in%Block+B+Block+D%in%Block+(A%in%Block):B+(A%in%Block):(D%in%Block)+B:Block
+(D%in%Block):B+(A%in%Block):(D%in%Block):B

My questions are: 

1. Is the model correct?
2. How do I type in the model information for lme?

Thanks in advance,

Matthias






-- 
NEU: WLAN-Router für 0,- EUR* - auch für DSL-Wechsler!
GMX DSL = supergünstig & kabellos http://www.gmx.net/de/go/dsl