, 70 (1), 108-113

# An Example of an Improvable Rao-Blackwell Improvement, Inefficient Maximum Likelihood Estimator, and Unbiased Generalized Bayes Estimator

Tal Galili et al. Am Stat.

## Abstract

The Rao-Blackwell theorem offers a procedure for converting a crude unbiased estimator of a parameter θ into a "better" one, in fact unique and optimal if the improvement is based on a minimal sufficient statistic that is complete. In contrast, behind every minimal sufficient statistic that is not complete, there is an improvable Rao-Blackwell improvement. This is illustrated via a simple example based on the uniform distribution, in which a rather natural Rao-Blackwell improvement is uniformly improvable. Furthermore, in this example the maximum likelihood estimator is inefficient, and an unbiased generalized Bayes estimator performs exceptionally well. Counterexamples of this sort can be useful didactic tools for explaining the true nature of a methodology and possible consequences when some of the assumptions are violated. [Received December 2014. Revised September 2015.].

Keywords: Improper prior; Minimal sufficiency; Uniform distribution; Uniformly minimum-variance unbiased estimator..

## Similar articles

### References

1. Abramovich F., and Ritov Y. (2013), Statistical Theory: A Concise Introduction, Boca Raton, FL: CRC Press, pp. 37–40.
1. Berkson J. (1955), “Maximum Likelihood and Minimum x 2 Estimates of the Logistic Function,” Journal of the American Statistical Association, 50, 130–162.
1. Bickel P.J., and Blackwell D. (1967), “A Note on Bayes Estimates,” The Annals of Mathematical Statistics, 38, 1907–1911.
1. Blackwell D. (1947), “Conditional Expectation and Unbiased Sequential Estimation,” The Annals of Mathematical Statistics, 18, 105–110.
1. Damilano G., and Puig P. (2004), “Efficiency of a Linear Combination of the Median and the Sample Mean: The Double Truncated Normal Distribution,” Scandinavian Journal of Statistics, 31, 629–637.