confidence interval that violates physical boundaries

#1
:wave::wave::wave:
Hi, Colleagues,
A model is supposed to predict a value that represents proportion, namely, the predicted value should be in [0,1]. However, model is just a linear regression, producing confidence intervals violating the boundaries of [0,1]. Of course it is not an adequate model. However, what is the statistical term to describe such symptom of a model, Namely, confidence interval violating physical boundaries of objects being modeled? If you could provide a reference, it would be highly appreciated!

John Zi
 

hlsmith

Not a robit
#2
Your variable should be any number between 0 and 1, correct? Some times, maybe, these limits are referred to as celling or floor. Sorry, no reference.

P.S., Well I was just thinking, not sure if there may or may not be much on this, since it seems like a case of model misspecification. I would look to see how others handle these data.