fim.likelihood_model: Default FIM method using Monte Carlo estimation

In likelihood.model: Likelihood-Based Statistical Inference in the Fisherian Tradition

Default FIM method using Monte Carlo estimation

Description

Computes the Fisher information matrix by Monte Carlo simulation using the negative expected Hessian approach. For each of n_samples replicates, generates a single-observation dataset via rdata, computes -hess_loglik(single_obs, theta), and averages. The result is n_obs * I_1(theta) where I_1(theta) is the per-observation FIM.

Usage

## S3 method for class 'likelihood_model'
fim(model, ...)

Arguments

model	A likelihood model
...	Additional arguments passed to rdata

Details

This default requires the model to implement rdata and hess_loglik (or loglik, since hess_loglik falls back to numerical differentiation).

Value

Function that takes (theta, n_obs, n_samples, ...) and returns FIM matrix

likelihood.model documentation built on March 19, 2026, 9:07 a.m.