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
- :
- Discussions
- :
- Plotting confidence intervals in parametric survival analysis(Weibull)

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

Mar 11, 2014 11:20 AM
(1369 views)

Hi all,

I am doing a parametric survival analyses (Weibull), and I would like to plot a curve similar to the one below. I could plot the mean (blue trace below), as JMP gave me the formula for it, but I am not able to plot the confidence intervals as JMP wont give the formula. However I could see the plot (mean and CIs) in the "profiler" of the platform.

The formula to compute row wise mean quantiles that JMP gave me is below, where : Probability is a column with numbers from 0.001 to 1 by 0.001. Delta, Intercept and AGE are regression predictions. Is it possible to compute row wise confidence intervals using the same formula, knowing standard errors?

Weibull Quantile( : Probability, 1 / Delta, Exp(Intercept+ AGE* :age )

Any suggestions are appreciated.

Thanks in advance.

1 REPLY

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

Jan 26, 2015 7:48 AM
(1221 views)
| Posted in reply to message from mikethejumper 03/11/2014 02:20 PM

Hello,

Please see my response to Save formula for 95% CI in parametric survival analysis. In your example, you only have one X variable (AGE), so you might be able to use Fit Life by X.

Regards,

Michael

Michael Crotty

Sr Statistical Writer

JMP Development

Sr Statistical Writer

JMP Development