Michael McCulloch wrote:
I would like to learn how to identify the last observation
of each individual subject within a longitudinal data set.
I'm using the hip2.dta data set, and have run _stsplit_ to
create one observation per failure time for each subject.
Note that subject id==1 observed a failure during observation
time, whereas subject id==48 did not.
use hip2.dta, clear
stsplit, at(failures) riskset(riskid)
sort id time0
list id time0 time1 protect fracture if id==1 | id==48
In order to estimate a subject's probability of being
censored, I will create a new variable, C, which is equal to
zero for a subject's last failure time if the subject was not
censored, and is equal to one subject was censored.
How can I identify the last observation of each individual
subject within a longitudinal data set, so that I can create
my new variable without having to manually search for that
last observation?
==============================================================
Using the example from [ST] stsplit:
webuse diet.dta , clear
stset dox , failure(fail) origin (time dob) enter(time doe) scale(365.25) id(id)
stsplit ageband , at(40(10)70)
bysort id (_t) : egen maxt = max(_t)
Now, the last observation period for each person is the period
where maxt == _t.
Hope this helps
Svend
________________________________________________________
Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(Institute of Public Health, Department of Epidemiology)
Vennelyst Boulevard 6
DK-8000 Aarhus C, Denmark
Phone, work: +45 8942 6090
Phone, home: +45 8693 7796
Fax: +45 8613 1580
E-mail: [email protected]
_________________________________________________________
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
