scholarly journals Non-Parametric Tests for Testing of Scale Parameters

2021 ◽  
Vol 19 (1) ◽  
pp. 2-21
Author(s):  
Manish Goyal ◽  
Narinder Kumar
Keyword(s):  
Simulation Study ◽  
Null Distribution ◽  
Asymptotic Power ◽  
Pitman Efficiency ◽  
Scale Parameters ◽  
U Statistics ◽  
Non Parametric

One of the fundamental problems in testing of equality of populations is of testing the equality of scale parameters. The subsequent usages for scale are dispersion, spread and variability. In this paper, we proposed non-parametric tests based on U-Statistics for the testing of equality of scale parameters. The null distribution of proposed tests is developed and its Pitman efficiency is worked out to compare proposed tests with respect to some existing tests. Simulation study is carried out to compute the asymptotic power of proposed tests. An illustrative example is also provided.

scholarly journals A comparative study of the Gini coefficient estimators based on the linearization and U-statistics Methods

2017 ◽  
Vol 40 (2) ◽  
pp. 205-221 ◽  
Author(s):  
Shahryar Mirzaei ◽  
Gholam Reza Mohtashami Borzadaran ◽  
Mohammad Amini
Keyword(s):  
Comparative Study ◽  
Simulation Study ◽  
Gini Coefficient ◽  
Gini Index ◽  
Real Data ◽  
Linearization Method ◽  
U Statistics ◽  
The Gini Coefficient

In this paper, we consider two well-known methods for analysis of the Gini index, which are U-statistics and linearization for some incomedistributions. In addition, we evaluate two different methods for some properties of their proposed estimators. Also, we compare two methods with resampling techniques in approximating some properties of the Gini index. A simulation study shows that the linearization method performs 'well' compared to the Gini estimator based on U-statistics. A brief study on real data supports our findings.

scholarly journals Estimation of P(Y < X) in a Four-Parameter Generalized Gamma Distribution

2016 ◽  
Vol 41 (3) ◽  
Author(s):  
M. Masoom Ali ◽  
Manisha Pal ◽  
Jungsoo Woo
Keyword(s):  
Maximum Likelihood ◽  
Closed Form ◽  
Importance Sampling ◽  
Simulation Study ◽  
Maximum Likelihood Method ◽  
Sampling Procedure ◽  
Likelihood Method ◽  
Scale Parameters ◽  
Generalized Gamma ◽  
Modified Maximum Likelihood

In this paper we consider estimation of R = P(Y < X), when X and Y are distributed as two independent four-parameter generalized gamma random variables with same location and scale parameters. A modified maximum likelihood method and a Bayesian technique have been used to estimate R on the basis of independent samples. As the Bayes estimator cannot be obtained in a closed form, it has been implemented using importance sampling procedure. A simulation study has also been carried out to compare the two methods.

Estimation of the Parameters of Triangular Distribution by Order Statistics

2003 ◽  
Vol 54 (1-2) ◽  
pp. 45-56 ◽  
Author(s):  
Philip Samuel ◽  
P. Yageen Thomas
Keyword(s):  
Order Statistics ◽  
Triangular Distribution ◽  
Unbiased Estimators ◽  
Product Moments ◽  
Scale Parameters ◽  
U Statistics ◽  
Best Linear Unbiased ◽  
Best Linear Unbiased Estimators ◽  
Moments Of Order Statistics ◽  
Single And Product Moments

In this paper, we derive explicit expressions for the single and product moments of order statistics arising from the standard triangular distribution. Best linear unbiased estimators of the location and scale parameters of a triangular distribution based on order statistics are obtained. The efficiencies of these estimators are also compared with estimators based on U-statistics

Non-parametric optimal service pricing: a simulation study

2016 ◽  
Vol 14 (2) ◽  
pp. 142-155 ◽  
Author(s):  
Asif Muzaffar ◽  
Shiming Deng ◽  
Ammar Rashid
Keyword(s):  
Simulation Study ◽  
Service Pricing ◽  
Optimal Service ◽  
Non Parametric

Multivariate Denoising and Missing Data Estimation for Heavy-Tailed Signals

2019 ◽  
Vol 18 (03) ◽  
pp. 1950016
Author(s):  
Ferdos Gorji ◽  
Mina Aminghafari
Keyword(s):  
Linear Regression ◽  
Simulation Study ◽  
Parametric Method ◽  
Matrix Decomposition ◽  
Heavy Tailed ◽  
Multivariate Signals ◽  
Missing Data Estimation ◽  
Data Estimation ◽  
Robust Linear Regression ◽  
Non Parametric

This study focuses on heavy-tailed noise reduction in multivariate signals, with no knowledge of their forms. We propose a non-parametric multivariate denoising technique which is robust to heavy-tailed noise. Using a univariate robust linear regression, we construct a multivariate non-parametric method. We design a robust matrix decomposition and, consequently, propose a robust procedure including this new decomposition. In addition, we develop a robust procedure for the imputation of the missing points of the signals. The key advantage of our methods over the previous tools is the robustness to the heavy-tailed observations. The results of our simulation study confirm the good performance of the proposed methods.

Sign in / Sign up

Export Citation Format

Share Document