turn on suggestions

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

Showing results for

- JMP User Community
- :
- Discussions
- :
- Can JMP be used to compare survival between a samp...

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
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jun 21, 2016 8:49 AM
(314 views)

3 REPLIES

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jun 22, 2016 8:07 AM
(229 views)

The survival launch window has a "grouping" option that would compare the survival of the "sample" population to the survival of the "standard" population. Here is a link to an example in the documentation:

http://www.jmp.com/support/help/Example_of_Survival_Analysis.shtml

This would not be paired by the individual pairs of matched samples but would look at the two groups as a whole. Is this what you are looking for?

Karen

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jun 22, 2016 8:45 AM
(229 views)

Hey Karen,

Thanks for the reply! I was more wondering with regard to the handling of the different data types. I have used that grouping function to perform survival analysis between different samples in which we have data for each individual. The problem I have is in comparing the survival with an expected survival for a specific population. For example, I want to know if my sample population consisting of all males with a mean age of 50 has a different survival curve from that of the general population that age and gender. This analysis is more complicated than I have done before because I am trying to compare individual sample data with collective population data. In one case, I have the date of birth and the date of death for each person. In the other case, I have just the death rate for people of the same age and gender.

-Charlie

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jun 23, 2016 1:24 PM
(229 views)

Charlie,

Could it be "as simple" (nothing is simple) as comparing the rate that you have to your estimate from your population using confidence intervals? If your median life time is 80 years (75, 85) and the WHO lifetime is 90 years then your lifetime is shorter, if the WHO is 83 then no different?

In other words, you have an estimate from WHO but no raw data. For your sample you have raw data from which to generate your estimate. Then you need a way to compare the two estimates. I like the confidence interval approach, maybe someone who has done more survival analysis than me will have another idea for you.

Karen