[R] removing dropouts from survival analysis

Bert Gunter bgunter.4567 at gmail.com
Mon Jan 23 22:45:14 CET 2017

Sorry. You may get private replies, but this *is* way OT on this list.
Try stats.stackexchange.com instead for statistical queries. Or,
better yet, find local consulting help. Non-random dropouts are a
difficult issue.

Bert Gunter

"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

On Mon, Jan 23, 2017 at 12:48 PM, Damjan Krstajic <dkrstajic at hotmail.com> wrote:
> Dear All.
> Apologies for posting a question regarding survival analysis, and not R, to the R-help list. In the past I received the best advices from the R community.
> The random censorship model (the censoring times independent of the failure times and vice versa) is one of the fundamental assumptions in the survival analysis. In the medical studies we have random entry to study and study end which is a censoring mechanism independent of the failure times. However, in reality we may have dropout subjects, lost to follow-up, which are censored by a different mechanism which may not be independent of the failure times. The inclusion of dropout subjects in the survival analysis may break the random censorship model and include bias in our estimates of survival with KM. I have studied papers on this subject (e.g. double sampling, copula approach for dependent censoring), but I have not found any research paper which examines the removal of dropout subjects from the survival analysis.
> I am alone in my research and would be grateful to hear thoughts on this subject. Thank you in advance and apologies for using the R-help list for my research question.
> DK
>         [[alternative HTML version deleted]]
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.

More information about the R-help mailing list