modeling an outcome that has a range from [-0.158 ; 1 ]

#1
Hello everyone,

I am trying to model a quality of life score that has a range [-0,158 ; 1], where values equal to one indicate the patient is fully healthy, values equal to 0 indicate the patient is dead, values smaller than 0 indicate a health state that is worse than death.

I assume general linear regression is not suitable since my response variable can always go outside the response range depending on the values of the covariates.

What is the suitable model parametrization to make sure that response stays always in the response range?

Thank you in advance.
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
Probably a better option out there, but you could standardize the DV and use beta regression. Can you post your sample size and a histogram of the DV!
 

katxt

Active Member
#3
It's not clear what you are looking for. Are you looking for a way to keep regression responses in the range [-0,158 ; 1]. Logistic regression keeps the response values between 0 and 1 and a simple adaption of it will give the range [-0,158 ; 1].
However, this is probably not what you want because 0 seems to have a different character from the rest of the range, as do the negative values.
Can you give us an example of what the model would do.