Skip to content
ml-recall

#fisher-information

2 questions from Probabilistic & Graphical Models

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

mediumAI-checkedProbabilistic & Graphical Models

Out of 10,000 people, 300 are infected. With a binomial likelihood, the maximum-likelihood estimate of the infection rate is γ^=300/10,000=0.03\hat\gamma = 300 / 10{,}000 = 0.03, and the Fisher information is I(γ)=n/(γ(1−γ))I(\gamma) = n / \big(\gamma(1 - \gamma)\big). What is the standard error 1/I(γ^)1 / \sqrt{I(\hat\gamma)}? Round to 4 decimals.

a number, 4 decimals