Creating a composite biomarker score using regression coefficients about cutpointr

[Thie1e]

Hi Laura,

I guess you could surely build a "standard" logistic regression model the way you described it using glm, for example.

But it seems to me this question does not directly relate to cutpointr. Generally, if you calculate cutpoints for your markers, just make sure not to feed dichotomized marker values into your regression model.

You can estimate a cutpoint on the resulting probabilities from the logistic regression model, if you are interested in diagnostic accuracy.

I would suggest to post a question to stats.stackexchange.com if you have a purely methodological / statistical question or to StackOverflow if you can't get the R code to work (questions directly related to cutpointr can of course still go here).

Best,
Christian

[LauraL231]

Thanks very much for the information, that's really helpful to know.
Thanks,
Laura