Dear All
Does any one know if the following survival analysis exists, and if so, is it
available in R?
I am trying to parametrically model survival where some events happen at time =
0. I am particularly interested in generating the 95% confidence interval
around the survival function over its full range (including time=0). For
example, the data below are for time (Time) to component failure (Status =1)
for a set of 10 new components. Failure is recorded in 9 components, the first
3 of which failed to start (Status=1, Time=0).
> Time
[1] 0 0 0 8 16 17 17 22 23 28
> Status
[1] 1 1 1 1 1 1 1 1 1 0
I know how to do this in two parts (using a parametric survival model where
Time>0 to develop confidence intervals over the range Time>0, and using the
proportion of failures to start to generate a binomial confidence interval for
Time=0). But I am hoping there is a single modelling approach - in this case it
would suggest likelihood of survival at Time=0 is <1, rather than the models I
am familiar with that indicate survival probabilityat Time=0 is always 1.
Any suggestion would be appreciated
Dr Terry Beutel
Senior Scientist
Agri-Science Queensland
********************************DISCLAIMER**************...{{dropped:15}}
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
