[R-sig-ME] Generalized Mixed Model (Poisson) for recurrent events study design (Sample Size estimation by simulation)

[si.fu at ntlworld.com]

Hello, 
 
I have a general help question that some of you might be able able to help. I have posed this to R-help list and I have been told that people reading this list might be best placed to help me.
 
I would like calculate sample size for a study (a two group comparison) based on the outcome of reduction on (recurrent) events (say hospital admissions). 
 
In a previous study, hospital admission rate of 140 admissions per 72 patients 
(over a 4 month period) has been observed. That is rate is about 1.9. In order 
to see the admission rate reduction of 50% over a 4 month period, i.e. 0.95, in 
a two group comparison (alpha 0.05) with appropriate power (say 80%) what sort 
of group sizes are needed. 

The number of hospital admissions per patient differ within  the four month period between 4 to none (i.e. poisson). So in order to account for between subject and within subject variation, lmer with poission model could be used for the simulation. I am grateful for your help in getting me started.
 
 
Many Thanks, 
 
Si.