Dear All,
Apologies for cross posting.
I am helping a friend in South America to design a survey to study, by
verbal autopsy, TB mortality. He wants to do that in the areas with higher
incidence rate, both rural and urban households.
I have suggested a cluster sampling. My question is do we have to do two
different calculations using different mortality rate to calculate the
sample size in urban and rural? Or could we use just one mortality rate, and
then depending on the distribution of the population (rural % and urban %)
should we estimate the number of persons surveyed in each area?
Thank you in advance
Julia Valderrama, M.D., M.P.H.
http://www.geocities.com/jvalder2001
_________________________________________________________________
Send and receive Hotmail on your mobile device: http://mobile.msn.com
|