hi
i have calculated a sample size based on the difference between two
groups (for condition a)
within each 'condition a' we have four groups - is it possible to adjust
the sample size to allow for differences in 'condition a' between the 4
groups - i would also like to examine the trend as the sample will be
collected from four different time periods
for info the estimates for condition a are 4% and 3% which gives a sample
size of 16172 for 99% confidence with 80% power
any comments greatly received
regards
ann
------------
ann e fitzmaurice
[log in to unmask]
|