I have a database with 61 patients in which the Hb was measured at 16 different time points. The dates of those time points are (of course) not the same for all patients.
Of those 61 patients, approximately half have a short survival and half a long survival. I now want to see if the Hb differ between these 2 groups during the study (so for example: the Hb drops faster in the short survivors group than in the long survivors group). Does anyone know how to test this? With which tests and in which way in SPSS?
You can consider a linear mixed model where time and the survival indication variable are predictors. You can consider adding interactions and random effects if your data exploration phase suggests that.
Here you can see how it can be done in SPSS:
https://www.ibm.com/support/knowledgecenter/en/SSLVMB_23.0.0/spss/advanced/idh_mixl.html
Good luck!
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS