[R-sig-eco] anova designs for blocked sampling

[Nick Cutler]

I am investigating possible connections between long-term vegetation 
development and microclimate. I am interested in the relationship 
between temperature (the response variable) and two factors: 
Microtopographic Position (two levels: "hillock" & "hollow") and Terrain 
Age (three levels: "26 years", "161 years" & "848 years"). Temperature 
data were collected using automated data loggers: six data loggers were 
used for each level of Terrain Age (6 x 3 = 18 data loggers in total). 
The data loggers were deployed in pairs (one on a hillock, and one in an 
adjacent hollow) in three random locations on each terrain.

I would like to say something about how mean temperatures vary between 
hillock and hollow locations on terrain of different ages. However, I'm 
struggling to understand the implications of the restricted 
randomisation of a blocked design. Can someone advise me on the 
appropriate ANOVA formulation (and interpretation) in R?

Many thanks,

Nick
-- 
Dr Nick Cutler
Postdoctoral Research Assistant
School of Geography and the Environment
Oxford University Centre for the Environment
Dyson Perrins Building
South Parks Road
Oxford OX1 3QY
UK

Tel.: +44 1865 275 860