Dear all,
I would need to have some more details about the log-rank test which is performed to compare survival functions across strata. I know how the test statistic is calculated and I have seen that it is approximately distributed as a chi-square distribution. It seems to me that this approximate distribution is an asymptotic one. If this is true, could you please tell me which quantity should be large enough?
In fact, I wonder if the test is valid when the categorical variable which defines the strata contains categories which are poorly represented.
I will be very grateful for any help.
Regards,
Eve CORDA
Office national de la chasse et de la faune sauvage
(http://www.oncfs.gouv.fr)
BP 20
78612 Le Perray en Yvelines Cedex
FRANCE
Phone: +33 (0)1 30 46 60 64
Fax: +33 (0)1 30 46 60 99
[log in to unmask]
|