Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | roland andersson <rolandersson@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Analysis of SIR or HR with timevarying covariates and late entry big data |
Date | Fri, 25 Oct 2013 11:37:42 +0200 |
I solved it. There was no problem with memory even after stsplit on ageband and timeband and >73,000,000 posts. Roland 2013/10/25 roland andersson <rolandersson@gmail.com>: > I want to compare the incidence rate of a disease in 1st and 2nd > generation immigrants with that in the native population. I have > individual population data on total 11,000,000 individuals gathered > during a 20 year period. The data is year of birth, country of birth > of the individual and his/her parents, sex, date of immigration and > emigration, death and operation for the disease. You can only have the > disease once. The disease varies strongly with age and has been > decreasing over the study period. > > So this is time to event data with late entry. As the disease is > strongly related to age I think to use age as analysis time. If I use > Cox-regression I do not know how to adjust for the decreasing > incidence over time. > > I think I can do stsplit on year of birth and analysis time, but I am > afraid i will run into memory problem. > > May I use stir and adjust for year of birth? > > Help! > Roland Andersson > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/