Notice
You are now leaving support.minitab.com.
Click Continue to proceed to:
Use Fit Cox Model with Fixed Predictors only to describe the relationship between fixed predictors and survival, assuming proportional hazard rates. A predictor is fixed when you know the value at the beginning of the study and it does not change during the study period. You can include interaction and polynomial terms and perform stepwise selection of terms.
For example, analysts divide cancer patients by gender and administer drug treatments at various dose levels. The analysts record the survival times of patients and compare the relative risks for two groups.
Key results of comparative studies that use Cox regression often report relative risks for predictors and display graphs of the survival experience of subjects under different treatments. For example, a study on a cancer treatment concludes that the relative risk for two groups is 4, which means that the patients in one group are cancer-free at 4 times the rate of patients in the other group over the study period. Minitab displays relative risks for each variable so that you can easily compare the survival experience of subjects in different treatment groups.
To perform Cox regression with fixed predictors, choose .
Use Fit Cox Model in a Counting Process Form if each subject in your data can have multiple rows of observations or records that contain time intervals, (start, end], over which all the predictor values for the subject remain constant. The predictors can be fixed or time-dependent.
With this form of data input, subjects might also experience the event multiple times. This indicates that the event of interest is recurrent. For example, a subject might have a tumor that recurs several times during the study period.
You are now leaving support.minitab.com.
Click Continue to proceed to: