An estimator is asymptotically normal when a rescaled estimation error converges in distribution to a normal law.
If and for a deterministic constant , then . The continuous mapping theorem therefore givesand when . No independence between the two sequences is required. The deterministic limit matters: convergence of two separate nondegenerate marginal distributions does not determine their joint limit.
For example, if with and , then wherever the denominator is defined. This justifies substituting a consistent estimator of asymptotic variance when constructing a Wald confidence interval.
Suppose an estimating equation has the expansionwhere is nonsingular and the centered estimating function has covariance matrix . A central limit theorem gives asymptotic covariance for the rescaled error, or approximately for .
The transpose is essential when is not symmetric; the simplified form applies only in the symmetric case. Plugging in consistent estimates gives a sandwich covariance estimate. Regression heteroskedasticity-consistent standard errors and cluster-level generalized estimating equations use instances of this construction.
For independent Bernoulli random variables of fixed success probability , put and . The central limit theorem gives . Applying the delta method to the odds map , whose derivative is , givesThe ratio is undefined on the all-success event, whose probability is . Any finite extension there has the same limiting probability distribution, since that probability tends to zero. This is an asymptotic statement and does not assert an exact finite-sample variance of the unextended ratio. It is useful for uncertainty in estimated odds when the success probability stays away from one.
If a response has mean and variance , the delta method gives . Choosing proportional to makes this first-order variance independent of . For on positive means, the resulting transformation is the natural logarithm. This is a local approximation and requires the transformation to be defined on the observations; it does not make arbitrary normal responses positive or preserve an exact normal distribution.
For with and fixed , represent with having the standard normal distribution. Taking the natural logarithm of the absolute value gives the displayed identity. Its random second term has a common distribution, independent of , so this variance-stabilizing transformation gives an exactly constant variance. That variance is finite: the normal density is bounded near zero and , while normal tails control logarithmic growth at infinity. The transformation is defined almost surely, loses the sign of the mean, and does not produce an exact normal distribution. A zero mean makes the original observation identically zero and is outside its domain.
If converges in distribution to and is Hadamard differentiable at tangentially to a space containing the limit, the displayed transformation rule holds under the usual measurability and tight separable-support conditions. The variables must belong to the domain of .
For an independent sample from , the maximum likelihood estimator is andThe parameter-dependent support makes the convergence rate rather than , so the regular maximum-likelihood central limit theorem does not apply.
Articles by others on the same topic
There are currently no matching articles.