In statistics, Hodges' estimator (or the Hodges–Le Cam estimator), named for Joseph Hodges, is a famous counterexample of an estimator which is "superefficient", i.e. it attains smaller asymptotic variance than regular efficient estimators. The existence of such a counterexample is the reason for the introduction of the notion of regular estimators.
Hodges' estimator improves upon a regular estimator at a single point. In general, any superefficient estimator may surpass a regular estimator at most on a set of Lebesgue measure zero.
Although Hodges discovered the estimator he never published it; the first publication was in the doctoral thesis of Lucien Le Cam.[1]
Suppose
\hat{\theta}n
\theta
L\theta
\theta
\sqrt{n}
\sqrt{n}(\hat\thetan-\theta) \xrightarrow{d} L\theta .
Then the Hodges' estimator
H | |
\hat{\theta} | |
n |
H | |
\hat\theta | |
n |
=\begin{cases}\hat\thetan,&if|\hat\thetan|\geqn-1/4,and\ 0,&if|\hat\thetan|<n-1/4.\end{cases}
\hat{\theta}n
[-n-1/4,n-1/4]
\theta
\begin{align} &
H | |
n | |
n |
-\theta) \xrightarrow{d} 0, when\theta=0,\\
H | |
&\sqrt{n}(\hat\theta | |
n |
-\theta) \xrightarrow{d} L\theta, when\theta ≠ 0, \end{align}
\alpha\inR
\hat{\theta}n
\theta ≠ 0
\theta=0
\hat{\theta}n
\theta=0
It is not true that the Hodges estimator is equivalent to the sample mean, but much better when the true mean is 0. The correct interpretation is that, for finite
n
E[X]
Le Cam shows that this behaviour is typical: superefficiency at the point θ implies the existence of a sequence
\thetan → \theta
\liminfE\thetan\ell(\sqrtn(\hat\thetan-\thetan))
\liminf
\thetan → \theta
In general, superefficiency may only be attained on a subset of Lebesgue measure zero of the parameter space
\Theta
Suppose x1, ..., xn is an independent and identically distributed (IID) random sample from normal distribution with unknown mean but known variance. Then the common estimator for the population mean θ is the arithmetic mean of all observations: . The corresponding Hodges' estimator will be
\,\geq\,n^\ |
The mean square error (scaled by n) associated with the regular estimator
x is constant and equal to 1 for all θs. At the same time the mean square error of the Hodges' estimator behaves erratically in the vicinity of zero, and even becomes unbounded as . This demonstrates that the Hodges' estimator is not regular, and its asymptotic properties are not adequately described by limits of the form (θ fixed,).