And using SPSS (for a change in environment) I get median overall
survival 9.9 months.
So I have stsum giving 10.1 months median survival time, I have stdes
giving 9.6 months time at risk and SPSS giving me 9.9 months.
I assume the difference between stdes and stsum is related to how you
treat the still patients not dead yet since the values are identical
for -stsum/stdes if status_fu==0-, equal to 8.6 months. The 8.6 months
would then be the patients already dead and I guess the increased time
you see above is related to the fact that the still living patients
contribute to increasing this value. However why should there be a
difference between the time-at risk and the survival time for the
living? And why is there a difference for all these values when I
compare to SPSS.
regards,
m
On Wed, Oct 7, 2009 at 1:16 PM, moleps islon <[email protected]> wrote:
> Dear listers,
> using stata v10.1 I obtain different results in my dataset for the
> median survival using stsum and stdes for the dataset, i.e.
>
> . stdes
>
> failure _d: status_fu == 0
> analysis time _t: cox_time
>
> |-------------- per subject --------------|
> Category total mean min median max
> ------------------------------------------------------------------------------
> no. of subjects 516
> no. of records 516 1 1 1 1
>
> (first) entry time 0 0 0 0
> (final) exit time 11.66499 .0666667 9.633333 74.9
>
> subjects with gap 0
> time on gap if gap 0
> time at risk 6019.1333 11.66499 .0666667 9.633333 74.9
>
> failures 453 .877907 0 1 1
> ------------------------------------------------------------------------------
>
> . help sts
>
> . stsum
>
> failure _d: status_fu == 0
> analysis time _t: cox_time
>
> | incidence no. of |------ Survival time -----|
> | time at risk rate subjects 25% 50% 75%
> ---------+---------------------------------------------------------------------
> total | 6019.133335 .07526 516 4.733333 10.06667 17.03333
>
>
> What is the difference in median time at risk per subject and median
> survival time? Which one to report?
>
> regards,
>
> M
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
