(Aalen, 1989) Write the additive model (4.54) in the following way
where the Xjare random variables.
a) Assume that one of the covariates, say Xp, is dropped from the model, for example, because it is unmeasured. Show that, if the Xjare independent, you still have an additive model where only the baseline regression function β0(t) is changed.
b) Assume that the Xjare dependent and multivariate normally distributed. How would the model change in this case when the covariate Xpis dropped?
Already registered? Login
Not Account? Sign up
Enter your email address to reset your password
Back to Login? Click here