R help - Mar 2014 - FrailtyHL package does not work

Dear all,

I want to describe the time interval between mammography screenings as a
function of several clinical and demographic variables. For each woman (ID), I
have multiple events and each event corresponds to the time interval between two
consecutive mammography screenings. Also, women's data sets come from ten
different primary health centres (PHC). I have data from 1995 up to 2013. I have
8828 women under study and each woman has at most 7 events (that is, 7 lines,
where the last line is always a censured event because it corresponds to the
date when the woman is lost to follow-up).

I tried to run the frailtyHL package in R:

frailtyHL(Surv(Time_2-Time_1,Event)~x+(1|ID)+(1|PHC),data=ficheiro.dados,RandDist="Normal",mord=1,dord=1,convergence=10^-4)

where, x is a generic independent variable.

but it gave the following error:

Error: cannot allocate vector of size 1.5 Gb
In addition: Warning messages:
1: Reached total allocation of 8172Mb: see help(memory.size) 
2: Reached total allocation of 8172Mb: see help(memory.size) 
3: Reached total allocation of 8172Mb: see help(memory.size) 
4: Reached total allocation of 8172Mb: see help(memory.size) 

What can I do to deal with this problem?

Thanks, in advanced, for your help.

Best regards,
Helena Mouri?o Nunes.

Dear Prof. Therneau,

thank very much for your answer. I don't know the reason why I didn't
receive your answer in my email. Today, I found it by chance at the internet.

I read the documentation about the package "coxme" and I think that it
fits my problem. I need to model multiple events for each woman (identified by
the ID): the time interval between consecutive mammographies. Also, women are
nested within the respective primary health centres (PHC). Is it correct to use
the following command ?

coxme(Surv(Time_1, Time_2,Event)~x+(1|PHC/ID),data=womenFile))

where, x is a generic independent variable.

Thank you very much for your help!

Regards,
Helena.
_______________________________________


I don't know much about the frailtyHL package, but from the description it
appears to be
fitting the same model as coxme.  The latter is designed to work with large data
sets.

Terry Therneau 


________________________________________
De: Maria Helena Mourino Silva Nunes
Enviado: sexta-feira, 14 de Março de 2014 19:02
Para: r-help@r-project.org
Assunto: FrailtyHL package does not work

Dear all,

I want to describe the time interval between mammography screenings as a
function of several clinical and demographic variables. For each woman (ID), I
have multiple events and each event corresponds to the time interval between two
consecutive mammography screenings. Also, women's data sets come from ten
different primary health centres (PHC). I have data from 1995 up to 2013. I have
8828 women under study and each woman has at most 7 events (that is, 7 lines,
where the last line is always a censured event because it corresponds to the
date when the woman is lost to follow-up).

I tried to run the frailtyHL package in R:

frailtyHL(Surv(Time_2-Time_1,Event)~x+(1|ID)+(1|PHC),data=ficheiro.dados,RandDist="Normal",mord=1,dord=1,convergence=10^-4)

where, x is a generic independent variable.

but it gave the following error:

Error: cannot allocate vector of size 1.5 Gb
In addition: Warning messages:
1: Reached total allocation of 8172Mb: see help(memory.size)
2: Reached total allocation of 8172Mb: see help(memory.size)
3: Reached total allocation of 8172Mb: see help(memory.size)
4: Reached total allocation of 8172Mb: see help(memory.size)

What can I do to deal with this problem?

Thanks, in advanced, for your help.

Best regards,
Helena Mouriño Nunes.