Suppose we use Maximum Likelihood estimation to estimate certain parameters in a model. Furthermore, suppose that the log likelihood function can not be solved analytically and thus must be optimised using Python or something equivalent. How then can I compute the standard errors of the estimates that follow from the optimisation?
Asked
Active
Viewed 1,128 times
1
-
1This is usually done by bootstrapping. – Moss Murderer Nov 07 '18 at 00:20
-
Other than the using the observed Fisher information? See e.g. https://stats.stackexchange.com/questions/68080/basic-question-about-fisher-information-matrix-and-relationship-to-hessian-and-s – Björn Nov 07 '18 at 08:30