Advances and Applications in Statistics
Volume 16, Issue 1, Pages 83 - 102
(May 2010)
|
|
ON ESTIMATION OF THE TRUNCATED PARETO DISTRIBUTION
Mei Ling Huang and Ke Zhao
|
Abstract: The Pareto distribution has many real world applications. There are theoretical difficulties in the inference of the Pareto distribution since it has infinite moments in heavy-tailed situations. This paper studies a truncated Pareto distribution to avoid these difficulties. We obtain a weighted estimation method to estimate the distribution function of the truncated Pareto distribution. The exact efficiency function of the new estimator relative to the classical estimator is derived. Properties of this efficiency function are studied. Monte Carlo simulation results confirm the theoretical conclusions. The paper concludes that the new weighted estimation method is more efficient than the classical estimation method in many situations. |
Keywords and phrases: efficiency, optimal weights, order statistics, truncation. *Research of author is supported by an NSERC Canada grant. |
|
Number of Downloads: 361 | Number of Views: 1272 |
|