Skip to main content

Mathematical Statistics II · Consistency, asymptotic normality, and delta methods

Let X₁,…,Xₙ be iid N(θ²,1), with parameter θ ≥ 0

Problem

Mathematical Statistics II practice problem

Let X1,…,XnX_1,\ldots,X_n be iid N(θ2,1)N(\theta^2,1), with parameter θ≥0\theta\ge0. Find the maximum-likelihood estimator θ^n\hat\theta_n.

For a fixed θ>0\theta>0, derive its usual root-nn limit. At θ=0\theta=0, find the scaling giving a nondegenerate limit, identify its CDF including any atom, and explain why the interior formula cannot be continued to the boundary.

Finally, along θn=c n−1/4\theta_n=c\,n^{-1/4}, with fixed c≥0c\ge0, find the distribution ofn1/4(θ^n−θn)n^{1/4}(\hat\theta_n-\theta_n)and the probability that the estimator equals zero. The parameter is identifiable on [0,∞)[0,\infty); explain how that fact can coexist with this nonregular local behavior.

Hint

Hint

Maximize first over the nonnegative mean u=θ2u=\theta^2, then transform back.

Check your work

Work the problem yourself first. Then open it in Training to check your answer and read the full worked solution.

The answer check and full solution for this problem come with ProofAnvil Practice membership ($19 USD monthly). See membership. Or start with the free Mathematical Statistics II sample problem: Try the free sample problem.

More Mathematical Statistics II practice problems