I am doing a meta-analysis of the validity of age as a prognostic factor. Different studies report different categories for age, making them difficult to combine. For example, if a study reports hazard ratios for 3 categories e.g.
Age under 50 - hazard ratio 1 (reference)
Age 50 - 59.9 - hazard ratio 1.89 (1.09, 3.33)
Age over 60 - hazard ratio 3.03 (1.67, 5.56)
How can I calculate a hazard ratio comparing those aged under 50 with those aged over 50 i.e. how can I combine group 2 and 3?
Thanks a lot
Hi Stella,
In order to pool the HR you can use the Excel document I have provided answering this question: https://www.researchgate.net/post/Is_it_possible_to_pool_estimates_for_median_progression_free_survival_using_revman
I guess you can adapt it for your own purpose, and you should get the pooled HR that Rohit estimated above.
Hope it helps.
Béranger
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Meta-Analysis