• Communications for Statistical Applications and Methods
• /
• 제21권6호
• /
• pp.539-559
• /
• 2014

We derive the exact distribution of summation for random samples from uniform distribution and then compare the exact distribution with the approximated normal distribution obtained by the central limit theorem. To check the similarity between two distributions, we consider five existing normality tests based on the difference between the target normal distribution and empirical distribution: Anderson-Darling test, Kolmogorov-Smirnov test, Cramer-von Mises test, Shapiro-Wilk test and Shaprio-Francia test. For the purpose of comparison, those normality tests are applied to the simulated data. It can sometimes be difficult to derive an exact distribution. Thus, we try two different transformations to find out which transform is easier to get the exact distribution in terms of calculation complexity. We compare two transformations and comment on the advantages and disadvantages for each transformation.

• Communications for Statistical Applications and Methods
• /
• 제29권4호
• /
• pp.403-411
• /
• 2022

This article presents an independence test between pairs of interval censored failure times. The Mantel-Haenszel test is commonly applied to test the independence between two categorical variables accompanied with a strata variable. Hsu and Prentice (1996) applied a Mantel-Haenszel test to the sequence of 2 × 2 tables formed at the grids which are composed of failure times. In this article, due to unknown failure times, the suitable grid points should be determined and the status of failure and at risk are estimated at those grid points. We also consider a weighted test statistic to bring a more powerful test. Simulation studies are performed to evaluate the power of test statistics under finite samples. The method is applied to analyze two real data sets, mastitis data from milk cows and an age-related eye disease study.

• Journal of the Korean Statistical Society
• /
• 제24권2호
• /
• pp.419-437
• /
• 1995

Given the specific mean shift outlier model, several standard approaches to obtaining test statistic for outliers are discussed. Each of these is developed in detail for the nonlinear regression model, and each leads to an equivalent distribution. The geometric interpretations of the statistics and accuracy of linear approximation are also presented.

• 응용통계연구
• /
• 제22권2호
• /
• pp.237-248
• /
• 2009

신용평가 연구에서 부도와 정상의 분포함수들의 동일성을 검정하는 비모수적 방법으로 Kolmogorov-Smirnov 검정법 이외에 Clamor-Yon Mises, Anderson-Darling, Watson 검정방법을 소개한다. 부도와 정상의 분포함수들의 선형결합된 부도율의 분포함수에 관한 전체적인 정보는 파악되어 잘 알고 있다. 모집단의 분포함수를 알고 있다는 가정 하에 Clamor-Von Mises, Anderson-Darling, Watson 검정통계량의 수정통계량을 제안한다. 신용평가자료와 유사한 성격을 갖는 다양한 부도율의 확률분포로부터 스코어를 생성하여 본 연구에서 제안한 수정통계량을 비교 토론한다.

• 응용통계연구
• /
• 제30권4호
• /
• pp.513-528
• /
• 2017

두 표본 집단이 동일한 분포를 따르는지 비교하기 위해 분포무관 검정이 많이 사용된다. 하지만 여러 검정법을 체계적으로 비교한 연구가 존재하지 않아서 각 검정법의 특성을 고려하여 연구 상황에 맞는 검정법을 선택하기가 어려웠다. 본 연구에서는 이표본 분포 동일성 검정에 해당하는 여러 분포무관 검정법들을 소개하고 체계적인 모의실험을 통해 그 성능을 비교하고자 한다. 두 표본이 각각 (1) 위치, (2) 척도, (3) 왜도, (4) 첨도, (5) 꼬리가중치가 다른 분포에서 추출된 상황에 대해 실험하였다. 실험 결과를 바탕으로 이표본 분포 동일성 검정법 사용에 대한 실용적인 지침을 제시하려고 한다.

• 응용통계연구
• /
• 제35권1호
• /
• pp.1-17
• /
• 2022

본 논문에서는 모수적 부트스트랩을 이용한 두 차등정보보호 히스토그램의 동질성 검정을 제안한다. 제안된 검정 방법은 차등정보보호 히스토그램과 적용된 차등정보보호 수준 정보만 있을 때에도 사용 가능하며, 비교하고자 하는 두 히스토그램에 적용된 차등정보보호의 수준이 다를 때에도 사용할 수 있다는 장점이 있다. 검정 방법의 성능을 평가하기 위해 미국과 한국의 연령별 인구분포 자료를 사용하고, 제 1종 오류의 확률이 잘 통제됨과 높은 검정력을 확인한다.

• Communications for Statistical Applications and Methods
• /
• 제10권2호
• /
• pp.535-543
• /
• 2003

A ranked set sample version of the sign test is proposed for testing hypotheses concerning the quantiles of a population characteristic by Kaur, et. al(2002). In this paper, we proposed the ranked set sample Wilcoxon signed rank test for quantiles under equal allocation. We obtain the asymptotic property and the asymptotic relative efficiencies of the proposed test statistic with respect to Wilcoxon signed rank test of simple random sample for quantiles under equal allocation. We calculate the ARE of test statistics, the proposed test statistic is more efficient than simple random sampling for all quantiles. The relative advantage of ranked set sampling is greatest at the median and tapers off in the tails.

• Journal of applied mathematics & informatics
• /
• 제3권2호
• /
• pp.235-244
• /
• 1996

Ranked-set sampling is useful when measurements are destructive or costly to obtain but ranking of the observations is rel-atively easy. The Wilcoxon signed rank test statistic based on the ranked-set sample is considered. We compared the asymptotic relative efficiencies of the RSS Wilcoxon signed rank test statistics with respect to the SRS Wilcoxon signed rank test statistic and the RSS sign test statistic. Throughout the ARE's the proposed test statistic is superior to the SRS Wilcoxxon signed rank test statistic and the RSS sign test statistic.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.921-934
• /
• 2004

We consider the problem of identifying and testing outliers in linear regression. First, we consider the scale-ratio tests for testing the null hypothesis of no outliers. A test based on the ratio of two residual scale estimates is proposed. We show the asymptotic distribution of test statistics and investigate the properties of the test. Next we consider the problem of identifying the outliers. A forward procedure based on the suggested test is proposed and shown to perform fairly well. The forward procedure is unaffected by masking and swamping effects because the test statistics used a robust scale estimate.

• Communications for Statistical Applications and Methods
• /
• 제23권6호
• /
• pp.563-574
• /
• 2016

In this study, we propose several simultaneous tests to detect the difference between means and variances for the two-sample problem when the underlying distribution is normal. For this, we apply the likelihood ratio principle and propose a likelihood ratio test. We then consider a union-intersection test after identifying the likelihood statistic, a product of two individual likelihood statistics, to test the individual sub-null hypotheses. By noting that the union-intersection test can be considered a simultaneous test with combination function, also we propose simultaneous tests with combination functions to combine individual tests for each sub-null hypothesis. We apply the permutation principle to obtain the null distributions. We then provide an example to illustrate our proposed procedure and compare the efficiency among the proposed tests through a simulation study. We discuss some interesting features related to the simultaneous test as concluding remarks. Finally we show the expression of the likelihood ratio statistic with a product of two individual likelihood ratio statistics.