cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar
saa2025
Level I

cubic spline with survival data

Hi guys, i have been looking for guidance with this for sometime but nothing. I am trying  to find the relationship between age and survival in a cohort. There is different follow-ups for patients, so I have to use survival analysis, with cox proportional hazard models. However, the relationship between age and survival is not linear. I want to use restricted cubic splines with this dataset. Is there an easy way to run this and visualize in JMP? I am looking for an output like this. thanks

nihms-444512-f0004.jpg

2 REPLIES 2
erich_gundlach
Level III

Re: cubic spline with survival data

Yes, you can do this in JMP:

  1. Select Analyze > Reliability and Survival > Fit Proportional Hazards.
  2. Populate the Time to Event and Censor boxes with the appropriate columns.
  3. Add your model effects to the lower box, including any interactions or polynomials.
  4. Select the model effect(s) to which you want to fit a restricted cubic spline (in your case, age). Click the red triangle next to "Attributes," and select Knotted Spline Effect (aka restricted cubic spline, Stone-Koo spline, etc.). Type in the number of knots you desire, and click OK.
  5. Click Run in the Model Specification dialog box.
  6. Click the red triangle next to Proportional Hazards Fit, and select Risk Ratios.

You can then construct a data table using the parameter estimates, risk ratios, etc. you obtained, and use that data to create graphs using JMP's Graph Builder that are similar to those you showed.

saa2025
Level I

Re: cubic spline with survival data

Thanks a lot. I got the following output from proportional hazards with 4 knots:

 

Untitled.jpg

 

How do I put this in the graph builder? Thanks!