Answers are grounded in this paper and cite their sources.
Consider a sample of size n from a regular exponential family in pₙ dimensions. Let θₙ denote the maximum likelihood estimator, and consider the case where pₙ tends to infinity with n and where \θₙ\ is a sequence of parameter values in Rpₙ. Moment conditions are provided under which \|θₙ - θₙ\| = Oₚ(√pₙ/n) and \|θₙ - θₙ - X̄ₙ\| = Oₚ (pₙ/n), where X̄ₙ is the sample mean. The latter result provides normal approximation results when p²ₙ/n → 0. It is shown by example that even for a single coordinate of (θₙ - θₙ), p²ₙ/n → 0 may be needed for normal approximation. However, if p3/2ₙ/n → 0, the likelihood ratio test statistic Λ for a simple hypothesis has a chi-square approximation in the sense that (-2 log Λ - pₙ)/√2pₙ →D N(0, 1).
No takes yet. Share an insight, caveat, or question.
Stephen Portnoy (1988) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: