turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- Landmark curve and adjustment for multiple compari...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-31-2016 04:24 PM

I want to do a landmark 1, 3 and 5 years analysis in SAS

i google it get information but i could not find it.

if i want to do the example data from sas website

https://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_lifetest_se...

how can i do it using the survival probability landmark curve for

0-500, more than 500 days and do the adjusted logrank for group by landmark.

similar graph in the attachement but i want to use the survival probability.

any advice i really appriciate.

Thanks very much

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-31-2016 05:45 PM

I'm not familiar with the term landmark curve but KM/survival curves appear to be what your after? I couldn't find anything via Google either, what's the subject area?

I'm moving your post to the Stats forum so it can hopefully get a better response there.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

05-31-2016 07:55 PM

Hi Reeza,

thanks for your reply

it's survival analysis. my follow up time 1 day to 12 years

i did a km curve for my data for 12 years period, treatmetn group has 4 (0,1,2,3)

i did it in stata, but they don't have adjusted logrank test ( i can find the answer for online), so

i found SAS command , i decided to use SAS for my analysis

to do the adjusted logrank test.

then i divide the data into 0-1 year( after 1 year if they died it's *censored)*

*then i divide the data into 2 to 3 years and 4 to 5 years*

*i did example in stata and SAS for adjustment for logrank test *

*data i took it from your website.*

i am attaching the file

thanks

Sugi