Solved – Can value of predicted probability from logistic model be greater than one


I derived a multivariate logistic model from my data containing a single binary response and five predictors.

I tried to calculate the predicted probabilities of one of the binary predictor (smoking) keeping the other, continuous, variables at their mean values. I get values greater than one.

Is it possible to get predicted probability value greater than one? Can anyone elaborate?

Best Answer

The OP has explained in comments that they by error used the R glm function, but forgot to specify the argument family=binomial, that is, used the default gaussian family (with identity link.) But that is the usual (least squares) linear regression, not logistic regression, and clearly can give predictions outside the interval $(0,1)$.