首页> 外文期刊>The Open Statistics & Probability Journal >A New Method of Estimation of Size-Biased Generalized LogarithmicSeries Distribution
【24h】

A New Method of Estimation of Size-Biased Generalized LogarithmicSeries Distribution

机译:大小有偏广义对数级数分布估计的新方法

获取原文
       

摘要

In this paper, a size-biased generalized logarithmic series distribution (SBGLSD) is introduced and its momentsare obtained. The estimates of the parameters of SBGLSD are obtained by employing the method of moments and a proposednew method of estimation. The new proposed method of estimation uses the non-zero frequency of a variable onlyup to a finite value. In this method, the estimation of only one parameter is needed and of the other is obtained by the relationshipamong the parameters by counting the number of non-zero frequency classes. The method is found very simpleand quick to apply in practice. Extensive simulations are performed to compare the performances of the proposed and themoment method of estimation mainly with respect to their biases and mean squared errors (MSE’s), for different samplesizes and of different parametric values. Comparison has been made among different estimation methods by means ofPearson’s Chi-square, Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) techniques.
机译:本文介绍了一个大小有偏的广义对数级数分布(SBGLSD),并获得了矩。通过采用矩量法和提出的新的估计方法获得了SBGLSD参数的估计值。提出的新估计方法仅使用变量的非零频率直到有限值。在这种方法中,仅需要估计一个参数,而另一个参数则可以通过计算非零频率等级的数量与参数之间的关系来获得。发现该方法非常简单并且可以在实践中快速应用。针对不同的样本量和不同的参数值,进行了广泛的仿真,以比较建议的和矩量估算方法的性能,主要是针对其偏差和均方误差(MSE)。通过皮尔逊(Pearson)的卡方,赤池信息准则(AIC)和贝叶斯信息准则(BIC)技术对不同的估算方法进行了比较。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号