R help - Jul 2010 - Multilevel survival model

* Please cc me if you reply as I am a digest subscriber *

Hi,
I am wondering how I can run a multilevel survival model in R? Below is
some of my data.
> head(bi0.test)
  childid famid lifedxm     sex      age delta
1   22.02    22 CONTROL   MALES 21.36893     0
2   13.02    13   MAJOR   MALES 21.18001     0
3   64.02    64 CONTROL   MALES 20.09377     0
4    5.02     5 CONTROL FEMALES 19.94524     0
5  183.02   183 BIPOLAR FEMALES 19.87406     0
6   37.02    37 BIPOLAR   MALES 19.83847     0

Where age is my time variable and delta is development of thought
problems (0 = No; 1 = Yes). My covariate of principle interest is
mother's diagnosis (control, major depression, and bipolar) and I am
principle interested in examining how the survival (not developing
thought problems) differs by this covariate. However, I have siblings in
my data set (famid) and I would like to account for this shared
variability. How might I do this in R? Can I do it with the survival
library? If possible, I'd also like to control for sex.

Thanks,
Chris

-- 
Christopher David Desjardins
PhD student, Quantitative Methods in Education
MS student, Statistics
University of Minnesota
192 Education Sciences Building
http://cddesjardins.wordpress.com

On Thu, Jul 22, 2010 at 8:23 AM, Christopher David Desjardins
<desja004 at umn.edu> wrote:
> * Please cc me if you reply as I am a digest subscriber *
>
> Hi,
> I am wondering how I can run a multilevel survival model in R? Below is
> some of my data.
>
>> head(bi0.test)
> ?childid famid lifedxm ? ? sex ? ? ?age delta
> 1 ? 22.02 ? ?22 CONTROL ? MALES 21.36893 ? ? 0
> 2 ? 13.02 ? ?13 ? MAJOR ? MALES 21.18001 ? ? 0
> 3 ? 64.02 ? ?64 CONTROL ? MALES 20.09377 ? ? 0
> 4 ? ?5.02 ? ? 5 CONTROL FEMALES 19.94524 ? ? 0
> 5 ?183.02 ? 183 BIPOLAR FEMALES 19.87406 ? ? 0
> 6 ? 37.02 ? ?37 BIPOLAR ? MALES 19.83847 ? ? 0
>
> Where age is my time variable and delta is development of thought
> problems (0 = No; 1 = Yes). My covariate of principle interest is
> mother's diagnosis (control, major depression, and bipolar) and I am
> principle interested in examining how the survival (not developing
> thought problems) differs by this covariate. However, I have siblings in
> my data set (famid) and I would like to account for this shared
> variability. How might I do this in R? Can I do it with the survival
> library? If possible, I'd also like to control for sex.
as usual, R has an embarrassment of riches

see <http://glmm.wikidot.com/faq> under the heading 'Mixed Modeling
Packages' - particularly under the subheading 'extensions'

If you want to stick with the survival package the frailty function
may be of interest.

The package bayesSurv would be worth looking at as well.

As an aside: I assume many (most?) of your groups are singletons -- I
wonder what impact that will have on estimators if you are including
famid as a random effect.

Kingsford


>
> Thanks,
> Chris
>
> --
> Christopher David Desjardins
> PhD student, Quantitative Methods in Education
> MS student, Statistics
> University of Minnesota
> 192 Education Sciences Building
> http://cddesjardins.wordpress.com
>
> ______________________________________________
> R-help at 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.
>

check out the coxme and the kinship packages, both have the capability to fit
the Cox proportional hazard model in a multi-level setting, or you could use
glmer in lme4 to fit discrete-time (logistic) models with random intercepts.
CS

-----
Corey Sparks, PhD
Assistant Professor
Department of Demography and Organization Studies
University of Texas at San Antonio
501 West Durango Blvd
Monterey Building 2.270C
San Antonio, TX 78207
210-458-3166
corey.sparks 'at' utsa.edu
https://rowdyspace.utsa.edu/users/ozd504/www/index.htm
-- 
View this message in context:
http://r.789695.n4.nabble.com/Multilevel-survival-model-tp2298756p2300071.html
Sent from the R help mailing list archive at Nabble.com.