Citations 0
November 3, 2004

Androgen Suppression Plus Radiation Therapy for Prostate Cancer—Reply

JAMA. 2004;292(17):2084-2085. doi:10.1001/jama.292.17.2085-a

In Reply: In response to Dr Atkins’ questions, the log-rank P value of.04 was 2-sided and is the metric most frequently used when there is no a priori assumption made about early vs late differences, as was the case in our study at the time of its inception. This P value compares the entire distribution of both survival curves and not only the 5-year time point. There were no significant differences in the distribution of the known prognostic factors including age, PSA level, Gleason score, and clinical tumor category between the 2 treatment groups. Finally, the proportional hazard assumptions for the multivariable Cox models1 were tested and met.

First Page Preview View Large
First page PDF preview
First page PDF preview