Sample size for incidence rate

[Juan Zacarías]

Hi everyone!

I'm trying to calculate the sample size needed to obtain an incidence rate estimate with a certain precision. However, I cannot find the right commands in Stata. Could someone provide any help or ideas?

Thank you very much in advance!

Juan

[Andrew Lover]

You'll need to compare your captured rate to whatever the background rate might be, so a Poisson (or neg binomial etc.) model is appropriate.

http://www.stata.com/statalist/archive/2011-02/msg00477.html

http://www.amstat.org/sections/SRMS/Proceedings/papers/1987_028.pdf

And if you have a complex study design you might need to use -powersim- (from SSC).

[pavan pandey]

Hey Dr Andrew,

I plan to undertake a longitudinal study to calculate the 'lost to follow up' among TB patients. How can I calculate the sample size for this study using Stata?