st: Poultry data

["Shittu, Aminu" <ameen_vet@yahoo.com>]

Dear Statalisters,

I collected data from a commercial poultry farm, with the following variables:

1. -s_no- serial number (1 to 2783)
2. -date- date of data collection (first to last day of each of the 12 months)
3. -month- month of data collection (January to December)
4. -season- season of data collection (cold-dry, hot-dry, and warm-wet)
5. -pen_no- unique identifier for pen (1, 2, 3, 4, 5, 6, 7 and 8)
6. -time- time of data collection by day (from day 1 to day 365, or less in some pens, for each pen_no)
7. -housing_type- type of housing (open or sealed)
8. -age- age of flock in weeks in lay (continous)
9. -totlayers- total number of layers on the day of data collection (count)
10. -no_dead- number of layers that died on the day of data collection (count)
11. -mort_perc- percentage mortality of layers on the day of data collection

I am interested in looking at "factors associated with layer productivity in opened and sealed housing systems." I was just wondering whether I should do poisson modelling and survival analysis? Kindly assist me with a set of Stata commands for the initial model building and which variable should be included as a predictor, response and type of clustering in my model. Is survival analysis also fit for this kind of data as I have no record of each individual bird? Please note that pens are nested within housing here.

Best regards,

Aminu.


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/