Assume that the counting processes Ni(t), i = 1,2,...,n, have intensity processes of the form
where the Yi(t) are at risk indicators. We introduce
a) Show that the maximum likelihood estimator is
b) Show that is approximately normally distributed around the true value of β with a variance that may be estimated by 1/N(τ)
c) Use the result in question (b) to derive an approximate 95% confidence interval for ν = logβ.
Already registered? Login
Not Account? Sign up
Enter your email address to reset your password
Back to Login? Click here