Chapman–Robbins bound

From Wikipedia, the free encyclopedia

In statistics, the Chapman–Robbins bound or Hammersley–Chapman–Robbins bound is a lower bound on the variance of estimators of a deterministic parameter. It is a generalization of the Cramér–Rao bound; compared to the Cramér–Rao bound, it is both tighter and applicable to a wider range of problems. However, it is usually more difficult to compute.

The bound was independently discovered by John Hammersley in 1950,[1] and by Douglas Chapman and Herbert Robbins in 1951.[2]

Statement

Summarize
Perspective

Let be the set of parameters for a family of probability distributions on .

For any two , let be the -divergence from to . Then:

TheoremGiven any scalar random variable , and any two , we have .

A generalization to the multivariable case is:[3]

TheoremGiven any multivariate random variable , and any ,

Proof

By the variational representation of chi-squared divergence:[3] Plug in , to obtain: Switch the denominator and the left side and take supremum over to obtain the single-variate case. For the multivariate case, we define for any . Then plug in in the variational representation to obtain: Take supremum over , using the linear algebra fact that , we obtain the multivariate case.

Relation to Cramér–Rao bound

Usually, is the sample space of independent draws of a -valued random variable with distribution from a by parameterized family of probability distributions, is its -fold product measure, and is an estimator of . Then, for , the expression inside the supremum in the Chapman–Robbins bound converges to the Cramér–Rao bound of when , assuming the regularity conditions of the Cramér–Rao bound hold. This implies that, when both bounds exist, the Chapman–Robbins version is always at least as tight as the Cramér–Rao bound; in many cases, it is substantially tighter.

The Chapman–Robbins bound also holds under much weaker regularity conditions. For example, no assumption is made regarding differentiability of the probability density function p(x; θ) of . When p(x; θ) is non-differentiable, the Fisher information is not defined, and hence the Cramér–Rao bound does not exist.

See also

References

Further reading

Loading related searches...

Wikiwand - on

Seamless Wikipedia browsing. On steroids.