Solved – Survival analysis in SAS-is there a way to include a random effect with interval censored data

frailtyinterval-censoringrandom-effects-modelsassurvival

I'm trying to use some form of survival analysis (e.g. accelerated failure time or proportional hazards) to study seed germination time. My data is interval censored (also called "grouped-time") and has a random effect (also called "frailty"). How can I do this, ideally in SAS?

My seeds were on petri dishes that were censused on day 1, 3, 5, 8, and 14. These are interval censored, with a seed that germinated on d8 really germinated between day 6 and day 8.

PROC LIFEREG can handle interval censoring but as far as I know, it doesn't handle random effects. Seeds on the same petri dish are not independent, so I need to be able to include the dish as a random effect. I would like to make inferences about the mean or median time to germination for a seed grown under several treatment conditions (e.g. genotype, maternal temperature, seed temperature, & interactions)

Is there an approach that allows interval censoring as well as random effects? If so, how should I modify the SAS code below to include random effects? Do I need to switch procedures to something like PROC NLMIXED? If this is something that cannot be done in SAS, what software is the best/easiest to do this?

PROC LIFEREG DATA=survGeno2 plots=probplot;
TITLE "Interval censored AFT";
CLASS geno;
MODEL (start,fin)=geno;
RUN;

Best Answer

In SAS, you can use "proc phreg" and there is a "random" statement where you can assign your random effect.

for example: if variable (dish) is your cluster then

proc phreg data=survGeno2;
   class dish geno;
   model Time*Status(0)=geno;
   random dish; <- to assign the cluster effect here
   hazardratio 'Frailty Model Analysis' geno;
   run;

reference from: http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_phreg_sect056.htm

Here is a good teaching video here, please refer to https://www.youtube.com/watch?v=ZfgRBuM4u3U

There are other way to assign the distribution of frailty other than normal distribution. You can also use nlmix or others.

Related Question