A likelihood model for exact (uncensored) observations from a Weibull distribution. The model assumes that the observations are independent and identically distributed (i.i.d.).

This is a reference implementation demonstrating how to satisfy the likelihood_model concept with analytical derivatives. It provides:

  • loglik.weibull_uncensored: log-likelihood function

  • score.weibull_uncensored: score (gradient) function

  • hess_loglik.weibull_uncensored: Hessian of the log-likelihood

Analytical derivatives are 10-100x faster than the default numerical differentiation via numDeriv.

This model may also be used as a contribution in likelihood_contr_model for more complex models involving censoring.

weibull_uncensored(ob_col)

likelihood_exact_weibull(ob_col)

Arguments

ob_col

The name of the column in a data frame that contains the observations.

Value

A weibull_uncensored likelihood model object