survival analysis: flowering time (Rebecca Ross) - R-SIG-ecology

Sat, Oct 24, 2009 1:27 PM #

Hi Rebecca,

Could it fall in the framework of survival analysis with "competing events" or "competing risks".
In the medical field (not mine) it can be used to predict healing vs death, dying from disease A or B, etc. As far as I know, it assumes that the risk of competing events are independent.

I have not gone far enough to code it in R, but you can read on it in:
Kleinbaum DG, Klein M (2005) Survival Analysis, A Self-Learning Text, 2nd edn. Springer, London (and many other texts I'm sure)

Good luck!
Mick

PhD candidate
Natural Resource Sciences
McGill University, Canada

From: r-sig-ecology-bounces at r-project.org [r-sig-ecology-bounces at r-project.org] On Behalf Of r-sig-ecology-request at r-project.org [r-sig-ecology-request at r-project.org]
Sent: October 24, 2009 6:00 AM
To: r-sig-ecology at r-project.org
Subject: R-sig-ecology Digest, Vol 19, Issue 15

Send R-sig-ecology mailing list submissions to
        r-sig-ecology at r-project.org

To subscribe or unsubscribe via the World Wide Web, visit
        https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
or, via email, send a message with subject or body 'help' to
        r-sig-ecology-request at r-project.org

You can reach the person managing the list at
        r-sig-ecology-owner at r-project.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of R-sig-ecology digest..."


Today's Topics:

   1. survival analysis: flowering time (Rebecca Ross)
   2. Re: survival analysis: flowering time (Chris Gast)


----------------------------------------------------------------------

Message: 1
Date: Fri, 23 Oct 2009 23:15:02 +0100
From: Rebecca Ross <rebecca.ross at plants.ox.ac.uk>
Subject: [R-sig-eco] survival analysis: flowering time
To: "r-sig-ecology at r-project.org" <r-sig-ecology at r-project.org>
Message-ID:
        <756B64E07365AF43BE945A734A85E44528C36B0A54 at EXMBX03.ad.oak.ox.ac.uk>
Content-Type: text/plain; charset="us-ascii"

Dear All,

I am using survival analysis to compare flowering time between different populations in a field experiment. I have 3 possible outcomes:
a) flowered during experiment
b) had not flowered and were alive at harvest
c) had not flowered and were dead at harvest

Clearly, b) are right censored. But I am unsure what to do for c) as they were not censored (event will never happen), but equally I do not have a 'time to event' for them. To make things more complicated, dying before harvest is not independent of flowering time as being on the verge of death would make them also less able to flower, therefore recording them as being censored might be misleading.

Apologies if this is a naive question, it is my first time with survival analysis!

Any thoughts much appreciated!

Rebecca


------------------------------

Message: 2
Date: Fri, 23 Oct 2009 23:50:12 +0000 (UTC)
From: Chris Gast <cmgast at gmail.com>
Subject: Re: [R-sig-eco] survival analysis: flowering time
To: r-sig-ecology at r-project.org
Message-ID: <loom.20091024T014956-165 at post.gmane.org>
Content-Type: text/plain; charset=us-ascii

Hi Rebecca,

I am reminded of a statistical technique from preclinical biostatistics
(carcinogenicity) called the Peto prevalence-mortality test.  Essentially, it is
a method for assessing time to tumor development, when tumor development and
mortality are related.  I wonder if this, or some similar method can be adapted
to your situation, wherein tumor development is akin to flowering....?



Chris



------------------------------

_______________________________________________
R-sig-ecology mailing list
R-sig-ecology at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology


End of R-sig-ecology Digest, Vol 19, Issue 15