R help - Apr 2008 - Survival Regression with multiple events per subject

Dear R users!

I want to process a maximum likelihood estimation for a parametric
regression survival time model with multiple events per subject.

the STATA command for this survival regression is:

use survreg
stset failure(exercise), id(optionid)
local regressors itm posret negret
streg `regressors', distribution(weibull)

explanation:
stset declares data to be survival-time data;
exercise is the indicator variable, which shows if the subject is dead or
alive;
optionid is the multiple-record ID variable which means every subject has a
unique id and one subject can have multiple events. (see example below)

streg computes a maximum likelihood estimation for parametric regression
survival time models with multiple record data

now I search an equivalent command in R
I found the survival package but I have no solution for the use with
multiple records per subject.

library(survival)
survRegData <- survreg(formula=Surv(time,exercise)~itm+posret+negret,
data=Data, dist="weibull")
summary(survRegData)

My Question is: how can I modify the above command for the use of multiple
events per subject when the optionid is used for indicating the subject?

The dataset look like:

data  | exercisedate | itm    | posret  | negret | optionid| exercise | time
1996  | 1996         | 1.4518 | 0.05487 |-0.4485 |    1    |   0      |   1
1997  | 1997         | 2.4535 | 0.00385 |-0.2525 |    1    |   1      |   5
1998  | 1998         | 1.2523 | 0.04486 |-0.1482 |    2    |   1      |   8
1999  | 1999         | 3.4257 | 0.15287 |-0.8615 |    3    |   0      |   4
2000  | 2000         | 1.1457 | 0.07487 |-0.5485 |    3    |   1      |   5
2001  | 2001         | 2.4418 | 0.09553 |-0.3772 |    3    |   0      |   2


Thank you,

Fabian Hefner

> I want to process a maximum likelihood estimation for a parametric
> regression survival time model with multiple events per subject.
  Data sets with multiple records per subjects are used for several things, you 
need to tell me what it is that you want to accomplish.  Multiple records is a 
method, not a goal.
  
  1. Robust variance: If each observation is a separate measurement on the 
subject, with it's own covariates, time 0,  and endpoint, and you want a
"GEE"
type variance that accounts for the fact that multiple observations are for the 
same subject:
   survreg(Surv(time, exercise) ~ itm + posret + negret + cluster(id), ...
where id is a variable that is unique for unique subjects.
   
  2. Time dependent covariates: Each subject has one endpoint, but covariates 
change over time.  The bookkeeping for time dependent covariates is reasonably 
straightforward for proportional hazards models, but a major pain for an 
accelerated failure time (ACF) model.  I've thought about it but never 
implemented the feature in survreg, though this may change one day due to the 
increased interest in accelerated aging as a biological model among the 
researchers I work with (but don't hold your breath).  For example, if you 
smoked in your youth but later quit, in an ACF model this 'adds years'
to your
biological age which you never lose; the computer code has to keep track of 
covariate histories.  In a proportional hazards model today's risk = 
function(today's covariates), which is easier.  A weibull can be written in 
either ACF or PH form, survreg uses the acf style, I don't know which stata 
uses.

  3. Multiple events per subject, with a single time scale per subject.  This is
seen in reliability analysis where hazard = function of age.  Survreg does not 
handle this case either.  
  
  	Terry Therneau