I have retrieved a study that reports a logistic regression, the OR for the dichotomous outcome is 1.4 for the continuous variable ln(troponin) . This means that the Odds increase 0.4 every 2.7-fold in the troponin variable; but, is there any way of calculating the OR for a 1 unit increase in the Troponin variable?
I want to meta-analyze many logistic regressions, for which i need them to be in the same format (i.e some use the variable ln(troponin) and others (troponin). (no individual patient data is available)
I don't think there is a good way to incorporate this study in your data because if your main models are using OR for 1 unit increase of troponin it means that the logit of your outcome is linearly associated with troponin increase. (logit(p)~b*Troponin)
In the study you mentioned, the logit of your outcome is linearly associated with the log of troponin. Therefore you could not find a way to include it in your main model because you could not find a way to transform it correctly.
logit(p)~b*[ln(Troponin)] => the OR is defined per 1 unit increase of ln(troponin) so can not be converted linearly.
Just for the sake of completeness: it might be possible if there is a meaningful reference concentration of troponin you could refer to, but I doubt that there is such a value.
I presume, you can calculate the OR for a 1 unit increase in the Troponin variable by exponentiating the coefficient of the ln(troponin) variable in the logistic regression model. The coefficient of the ln(troponin) variable is 1.4, so the OR for a 1 unit increase in the Troponin variable is np.exp(1.4) = 4.0552.
- Badges
- Science topic
- Similar topics
- Correction