Dear Allstaters,
I am looking to calculate the power of a study with a fixed number of
patients when looking at survival interactions between treatment and
subgroup. I have used the Southwest Oncology Group website for this
(http://www.swogstat.org/stat/public/int_survival.htm) but it seems
to be coming up with levels of power that are too high and that are not
effected by the hazard rate in the subgroups. Has anyone used this site
and found the same thing. Is it a problem or is my knowledge not of a
high enough level?
Does anyone know of alternative methods of performing power
calculations for interactions in survival studies?
All help appreciated.
Kind regards,
David Lawrence PhD
ABC Trial Statistician
Clinical Trials & Statistics Unit
Institute of Cancer Research
Brookes Lawley Building
15 Cotswold Road
Sutton
Surrey SM2 5NG, UK
Tel: 020 8722 4187
Fax: 020 8770 7876
|