• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.405-412
• /
• 2003

In this paper, we consider two components system which the lifetimes have a bivariate weibull distribution with random censored data. Here the censoring time is independent of the lifetimes of the components. We construct large sample tests for independence and symmetry between two-components based on maximum likelihood estimators and the natural estimators. Also we present a numerical study.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 춘계학술대회
• /
• pp.121-126
• /
• 2003

In this paper, we consider two-components system which the lifetimes follow bivariate pareto model with censored data. We develop large sample tests for testing independence between two-components. Also we present simulated study which is the test based on asymptotic normal distribution in testing independence.

• Communications for Statistical Applications and Methods
• /
• 제13권2호
• /
• pp.409-418
• /
• 2006

We propose a nonparametric test procedure for the K-sample problem with grouped data. We construct the test statistics using the scores derived for the linear model based on likelihood ratio principle and obtain asymptotic distribution. Also we illustrate our procedure with an example. Finally we discuss some concluding remarks.

• 대한전자공학회논문지SP
• /
• 제44권6호
• /
• pp.118-123
• /
• 2007

본 논문에서는 잡음 환경에서의 음성 향상을 위해 향상된 Global Soft Decision (GSD) 기법을 제안한다. 통계적 모델을 바탕으로 한 음성 향상과 관련한 연구에서 GSD는 음성의 꼬리 부분에서 취약하다고 알려져 있으며, 이를 개선하기 위해 Smoothed Global Likelihood Ratio (SGLR)를 바탕으로 한 새로운 음성 향상 기법을 GSD에 적용한다. 제안된 방법은 다양한 잡음 환경에서 MOS 실험을 바탕으로 기존의 연구와 비교하였으며 우수한 성능을 보여주었다.

• Communications for Statistical Applications and Methods
• /
• 제30권4호
• /
• pp.411-421
• /
• 2023

This paper provides a new estimation equation based on the concept of a minimum distance between the empirical and theoretical distribution functions under the most widely used progressive Type-II censoring scheme. For illustrative purposes, simulated and real datasets from a three-parameter Weibull distribution are analyzed. For comparison, the most popular estimation methods, the maximum likelihood and maximum product of spacings estimation methods, are developed together. In the analysis of simulated datasets, the excellence of the provided estimation method is demonstrated through the degree of the estimation failure of the likelihood-based method, and its validity is demonstrated through the mean squared errors and biases of the estimators obtained from the provided estimation equation. In the analysis of the real dataset, two types of goodness-of-fit tests are performed on whether the observed dataset has the three-parameter Weibull distribution under the progressive Type-II censoring scheme, through which the performance of the new estimation equation provided is examined.

• Communications for Statistical Applications and Methods
• /
• 제17권2호
• /
• pp.275-292
• /
• 2010

동일 환자에게 적용된 2가지 진단검사의 정확성을 비교하기 위한 방법들 중에서 두개의 ROC곡선 아래 면적(AUC; Area Under Curve)의 차이는 주요한 잣대 중 하나이다. 본 연구에서는 AUC의 차이를 추정하는 방법으로 비모수적방법, 최대가능도법, 일반화추축량에 의한 방법, 붓스트랩방법의 4가지를 포함확률(coverage probability), 기대길이 (expected length) 측면에서 모의실험을 통하여 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.367-376
• /
• 2003

Two explicit estimators of the scale parameter in an exponential distribution based on Type-II censored samples are proposed by appropriately approximating the likelihood function. Then two type tests, including the modified Cramer-von Mises test and Kolmogorov-Smirnov test are developed for the exponential distribution based on Type-II censored samples by using the proposed estimators. For each test, Monte Carlo techniques are used to generate critical values. The powers of these tests are investigated under several alternative distributions.

• Communications for Statistical Applications and Methods
• /
• 제24권5호
• /
• pp.519-531
• /
• 2017

We consider goodness-of-fit test statistics for Weibull distributions when data are randomly censored and the parameters are unknown. Koziol and Green (Biometrika, 63, 465-474, 1976) proposed the $Cram\acute{e}r$-von Mises statistic's randomly censored version for a simple hypothesis based on the Kaplan-Meier product limit of the distribution function. We apply their idea to the other statistics based on the empirical distribution function such as the Kolmogorov-Smirnov and Liao and Shimokawa (Journal of Statistical Computation and Simulation, 64, 23-48, 1999) statistics. The latter is a hybrid of the Kolmogorov-Smirnov, $Cram\acute{e}r$-von Mises, and Anderson-Darling statistics. These statistics as well as the Koziol-Green statistic are considered as test statistics for randomly censored Weibull distributions with estimated parameters. The null distributions depend on the estimation method since the test statistics are not distribution free when the parameters are estimated. Maximum likelihood estimation and the graphical plotting method with the least squares are considered for parameter estimation. A simulation study enables the Liao-Shimokawa statistic to show a relatively high power in many alternatives; however, the null distribution heavily depends on the parameter estimation. Meanwhile, the Koziol-Green statistic provides moderate power and the null distribution does not significantly change upon the parameter estimation.

• Journal of the Korean Data and Information Science Society
• /
• 제21권2호
• /
• pp.317-325
• /
• 2010

In this paper, we develop four modified empirical distribution function (EDF) type tests using approximate maximum likelihood estimators for the half-logistic distribution based on multiply Type-II censored samples. We also propose modified normalize sample Lorenz curve polt and new test statistics. We compare the above test statistics in the sense of the power for various censored samples. We present an example to illustrate this method.

• 한국산학기술학회논문지
• /
• 제17권5호
• /
• pp.645-652
• /
• 2016

입력 랜덤 변수(input random variable)의 통계 모델링은 기계시스템의 신뢰성 해석(reliability analysis), 신뢰성 기반 설계(reliability-based design optimization), 해석모델의 통계적 검정(validation) 및 보정(calibration)을 위해 반드시 필요하다. 대표적인 통계모델링 기법에는 Akaike Information Criterion (AIC), AIC correction (AICc), Bayesian Information Criterion, Maximum Likelihood Estimation (MLE), Bayesian 방법 등이 있다. 이러한 방법들은 기본적으로 주어진 데이터로부터 후보 모델의 우도함수값을 이용하여 후보 모델 중 가장 적합한 모델을 선택하는 방법이며, 방법에 따라 데이터 수 혹은 파라미터의 수를 고려하여 모델을 선정한다. 하지만 실제 현장에서 데이터의 통계모델링을 하는 엔지니어는 각 방법의 장단점에 대한 이해가 부족하여 어떤 방법이 정확한 방법인지 몰라 통계모델링 수행 시 어려움이 있다. 본 논문에서는 다양한 통계모델링 방법들을 비교하고 각 방법의 장단점 분석을 통해 가장 적합한 모델링 기법을 제안하고자 한다. 각 방법의 검증을 위해 다양한 모분포를 가정하고 다양한 사이즈의 샘플을 임의로 생성하여 시뮬레이션을 수행하였으며, 실제 공학 데이터를 사용하여 통계모델링 방법의 유효성을 검증하였다.