What is the 'Cramer-Rao Lower Bound' (CRLB) for an unbiased estimator θ^\hat{\theta}θ^?
Var(θ^)≥1I(θ)Var(\hat{\theta}) \geq \frac{1}{I(\theta)}Var(θ^)≥I(θ)1
Var(θ^)≥I(θ)Var(\hat{\theta}) \geq I(\theta)Var(θ^)≥I(θ)
Var(θ^)=1nVar(\hat{\theta}) = \frac{1}{\sqrt{n}}Var(θ^)=n1
Var(θ^)=E[θ^]Var(\hat{\theta}) = E[\hat{\theta}]Var(θ^)=E[θ^]