[R] Question abt power calculation in multistrata data using Hmisc or other package

From: Vickie S <isvik_at_live.com>
Date: Sat, 16 Apr 2011 10:28:16 +0200

I have two unequal patient groups belonging to different geographic locations, treated by different drug regimens and their survival data. N1=150 and N2=60

In each group of data there are
three strata for one independent variable- treatment status (2=two drugs administered, 1=only one conventionally used drug administered, 0=no drug administered), dead or not and months to death. In order to calculate the statistical power necessary for carrying out this analysis, i tried to find appropriate function in Hmisc package. But it seems that it is meant for two groups such as reference/control versus cases.

This is the sample of data in each of the two groups:

Treatment_stat Death MonthsToEvent

1 0 60.0
2 1 55.3
0 1 36.7
0 1 39.9

number of cases in treatment strata :
group 1: n12=110; n11=25;n10=15 (N2=150) group 2: n22=43;n21=8;n20=9 (N2=60)

output indicates significant different survival in group 1 data but not in group 2. How can one be sure that the lack of significance of survival difference is true in group 2 and it is not because of fewer number of cases in group 1 ?
Is there any function for this type of calculations in Hmisc or some other R package.


        [[alternative HTML version deleted]]

R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Sat 16 Apr 2011 - 08:31:26 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sat 16 Apr 2011 - 09:30:30 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive