I am combining multiple studies on mortality in CKD per different categories of 25(OH)D. One study have reported Hazard Ration per 1 unit standard deviation increase in 25(OH)D and some reported Hazard Ratios (HR or relative risk). what is the difference between HR/SD and HR? Is there any possibility to convert HR/SD to HR? Assuming both types of study measure mortality, can both be combined together? Thank you.
HR per 1 standard deviation reveals that they have standardized that predictor before entering into model. Namely they used standardized values instead of its ordinary values. A unit increase in HR per SD should be interpreted as an SD unit increase in ordinary HR. So you can revert back to HR using HR/SD if you know SD.
Take log of HR/SD and divide by SD. Then exponentiate it. This way you will get HR.
Dear Mehmet,
Thank you for your response. I did it but the log of HR/SD became negative.
In the paper, this is the HRs per SD= 0.67(0.43-1.05)
and SD of 25(OH)D is 13.
Would you please direct me why my calculation I mean logarithm of HRs/SD resulted in negative number.
Thanks
It is not a problem.It is the regression coefficient which is negative, not HR. Do it as I described. You would get 0.969 for HR.
- Badges
- Science topic
- Similar topics
- Philosophy
- Esthetics
- Interpretation