[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
Constantine Daskalakis <constantine.daskalakis@mail.tju.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: -stsum- vs -stci- |

Date |
Tue, 19 Nov 2002 02:16:05 -0500 |

I am having trouble posting to the list -- I tried to post this yesterday but I haven't seen it appear... so, I'm trying once more.

I have noticed a slight discrepancy in the results from -stsum- and -stci- in failure-time data. Suppose that I have the following survival dataset with a total of 12 observations (6 each in 2 treatment groups), which are all events:

. list

group t fail

1. 1 1 1

2. 1 2 1

3. 1 3 1

4. 1 4 1

5. 1 5 1

6. 1 6 1

7. 2 11 1

8. 2 12 1

9. 2 12 1

10. 2 14 1

11. 2 15 1

12. 2 16 1

. stset t, failure(fail==1)

failure event: fail == 1

obs. time interval: (0, t]

exit on or before: failure

------------------------------------------------------------------------------

12 total obs.

0 exclusions

------------------------------------------------------------------------------

12 obs. remaining, representing

12 failures in single record/single failure data

101 total analysis time at risk, at risk from t = 0

earliest observed entry t = 0

last observed exit t = 16

I am interested in finding out the median survival time for each group.

-stsum- gives 3 and 14, but -stci- gives 3 and 12.

Looking at the data, the median for the second group appears to be 12.

My understanding is that both commands should be using the Kaplan-Meier and thus should come up with the same answer. Or not? Have I missed something?

. stsum, by(group)

failure _d: fail == 1

analysis time _t: t

| incidence no. of |------ Survival time -----|

group | time at risk rate subjects 25% 50% 75%

---------+---------------------------------------------------------------------

1 | 21 .2857143 6 2 3 5

2 | 80 .075 6 12 14 15

---------+---------------------------------------------------------------------

total | 101 .1188119 12 3 6 14

. stci, by(group) median

failure _d: fail == 1

analysis time _t: t

| no. of

group | subjects 50% Std. Err. [95% Conf. Interval]

-------------+-------------------------------------------------------------

1 | 6 3 .75 1 .

2 | 6 12 .75 11 .

-------------+-------------------------------------------------------------

total | 12 6 5.196152 2 14

________________________________________________________________

Constantine Daskalakis, ScD

Assistant Professor,

Biostatistics Section, Thomas Jefferson University,

125 S. 9th St. #402, Philadelphia, PA 19107

Tel: 215-955-5695

Fax: 215-503-3804

Email: constantine.daskalakis@mail.tju.edu

Webpage: http://www.kcc.tju.edu/Science/SharedFacilities/Biostatistics

*

* For searches and help try:

* http://www.stata.com/support/faqs/res/findit.html

* http://www.stata.com/support/statalist/faq

* http://www.ats.ucla.edu/stat/stata/

**References**:**st: RE: file wrote single opening quote***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

**Re: st: RE: file wrote single opening quote***From:*Ulrich Kohler <ukohler@sowi.uni-mannheim.de>

- Prev by Date:
**st: Wish List Re: Graphs** - Next by Date:
**st: dstdize labels fix** - Previous by thread:
**RE: st: RE: file wrote single opening quote** - Next by thread:
**Re: st: file wrote single opening quote** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |