Abstract
The Cauchy distribution is a peculiar distribution due to its heavy tail and the difficulty of estimating its location parameter. It is often cited as an example of the computational failure of the maximum likelihood method of estimation. The method of moment estimation fails and Bayesian estimation is very unstable. A new unbiased L-estimator based on order statistics is proposed, which is not only asymptotically efficient but outperforms existing L-estimators in terms of finite-sample efficiency.
Similar content being viewed by others
References
Bai ZC, Fu JC (1987) On the maximum-likelihood estimator for the location parameter of a Cauchy distribution. Can J Stat 15: 137–146
Balmer DW, Boulton M, Sack RA (1974) Optimal solutions in parameter estimation problems for the Cauchy distribution. J Am Stat Ass 69: 238–242
Barnett VD (1966a) Evaluation of the maximum likelihood estimator where the likelihood equation has multiple roots. Biometrika 63: 151–165
Barnett VD (1966b) Order statistics estimators of the location of the Cauchy distribution. J Am Stat Ass 61: 1205–1218
Bloch DA (1966) A note on the estimation of the location of the Cauchy distribution. J Am Stat Ass 61: 852–855
Chan LK (1970) Linear estimation of location and scale parameters of Cauchy distribution based on sample quantiles. J Am Stat Ass 65: 851–859
Cherkoffh H, Gastwirth JL, Johns MV (1967) Asymptotic distribution of linear combinations of functions of order statistics with applications to estimation. Ann Math Stat 38: 52–72
Copas JB (1975) On the unimodality of the likelihood for the Cauchy distribution. Biometrika 62: 701–704
David HA, Nagaraja HN (2003) Order statistics, 3rd edn. Wiley, Hoboken
Edwards AWF (1972) Likelihood. Cambridge University Press, Cambridge
Ferguson TS (1978) Maximum likelihood estimates of the parameters of the Cauchy distribution for samples of size 3 and 4. J Am Stat Ass 73: 211–213
Gabrielsen G (1982) On the unimodality of the likelihood for the Cauchy distribution: some comments. Biometrika 69: 677–688
Haas G, Bain L, Antle C (1970) Inferences for the Cauchy distribution based on maximum likelihood estimators. Biometrika 57: 403–408
Hinkley DC (1978) Likelihood inference about location and scale parameters. Biometrika 65: 253–261
Howlader HA, Weiss G (1988) On the Bayesian estimation of Cauchy parameters. Sankhye Ser B 50: 350–361
Johnson NL, Kotz S, Balakrishnan N (1994) Continuous univariate distributions, vol 1, 2nd edn. Wiley, New York
Lloyd EH (1952) Least-squares estimation of location and scale parameters using order statistics. Biometrika 39: 88–95
Mason DM (1981) Asymptotic normality of linear combinations of order statistics with a smooth score function. Ann Stat 9: 899–908
Moore DS (1968) An elementary proof of asymptotic normality of linear functionsof order statistics. Ann Math Stat 39: 263–265
Reeds JA (1985) Asymptotic number of roots of Cauchy location likelihood equations. Ann Stat 13: 775–784
Rothenberg RJ, Fisher FM, Tilanus CB (1965) A note on estimation from a Cauchy sample. J Am Stat Ass 59: 460–463
Sahran AE, Creenbcrg BG (eds) (1962) Contributions to order statistics. Wiley, New York
Stigler SM (1974) Linear functions of order statistics with smooth weight functions. Ann Stat 2: 676–693
Stigler SM (1979) Correction to linear functions of order statistics with smooth weight functions. Ann Stat 7: 466
Zhang J (2002) Powerful goodness-of-fit tests based on likelihood ratio. J R Stat Soc B 64: 281–294
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, J. A highly efficient L-estimator for the location parameter of the Cauchy distribution. Comput Stat 25, 97–105 (2010). https://doi.org/10.1007/s00180-009-0163-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-009-0163-y