[R] [R-sig-ME] lme nesting/interaction advice

[Federico Calboli]

On 12 May 2008, at 12:21, Nick Isaac wrote:

>
> I *think* the syntax for the model Federico wants is this:
>
> lmer(y~selection*males+ (selection|month) + (males|month))

I'll try and check against some back of the envelope calculations -- 
as I said, the model is, per se, nothing really new, and my data is  
fully balanced.

> My lme syntax is a bit rusty, so I'm not confident how to recode  
> with nested random effects, as in P&B p24.
>
>
> Two quick points:
> 1. I think Federico has caused some confusion on account of the way  
> he used the term 'crossing'

Sorry about that, I'll try to avoid causing such confusion in the  
future.

Cheers,

/F

--
Federico C. F. Calboli
Department of Epidemiology and Public Health
Imperial College, St. Mary's Campus
Norfolk Place, London W2 1PG

Tel +44 (0)20 75941602   Fax +44 (0)20 75943193

f.calboli [.a.t] imperial.ac.uk
f.calboli [.a.t] gmail.com