I am not sure that I have correctly interpreted the explanation for the use
of -tvc-
I have a data set of persons all of whom have hepatitis c and hiv. Half of
these persons take an antiretroviral but most did not start when they got
hiv. My end point is end stage liver disease (ESLD). Since hepC is a risk
factor for ESLD, I -st set- my data thus:
stset eslddate, id(id) failure(esld) origin(hcvdate) scale(365.25)
eslddate = date of esld
hcvdate = date of hcv
esld = end stage liver disease yes/no
Age at hcv infection (agehcv) is an important covariate I wish to include in
my model. I also know that antiretroviral exposure is a risk factor for
esld but the time on the drugs varies after hiv infection. I want to use
the time they were on antiretrovirals (arttime) as a time varying covariate
so I did this:
stcox agehcv, tvc(arttime)
I'm not sure if I have oversimplified the intention of this command. I wish
to take into account the varying effect of exposure to antiretrovirals.
*
* 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/
