Comparing hazard functions
Readings
- Hernán MA. The hazards of hazard ratios. Epidemiology (Cambridge, Mass.). 2010;21(1):13–5.
Slides
The slides for today’s class are available here and on Sakai as a PDF.
Notes
Until this point in the course, we have focused on estimating risk in a single sample. With these skills in hand, you are well positioned to describe the “natural course” (i.e., what is going on in the world without any intervention) and to make simple (crude) comparisons between groups.
But, there are times you might wish to compare quantities other than risk (such as hazard functions or survival time distributions). Moreover, you may wish to account for confounding in such comparisons using regression models.
This week’s topic is comparing hazards using the semiparametric Cox proportional hazards model.
After this lecture, take some time to reflect on what makes the Cox model semiparametric, rather than parametric or nonparametric.
Don’t forget that Thursday, March 11, is a University wellness day.
Videos
Recordings of lectures are available on the EPID 722 Sakai site.
Exercise
This week’s exercise is available on the EPID 722 Teams site. Please note that you will need to download the dataset from the data folder. The exercise questions can be found under /Class Materials/Exercises/Exercise 7/Exercise 7.docx. Sample SAS and R code can be found in the same folder.
Optional Reading
This lecture is intended to give you an overview of Cox models. For more “nuts and bolts” details, I recommend the following reading.
- Chapter 5 of “Survival Analysis Using SAS, Second Edition” by Paul Allison (PDF available from UNC library)
Questions
Please use the form below to submit your questions about this week’s reading.