• Proceedings of the Korean Society for Quality Management Conference
• /
• 2007.04a
• /
• pp.229-234
• /
• 2007

반도체 산업에서 동일제품을 여러 라인에서 생산하는 것은 일반적이다. 모든 라인에서 생산된 제품의 품질수준의 동일 여부는 반도체 공정 계측데이터의 동일성 여부로 결정된다. 이러한 의사결정에 앞서 계측데이터를 생산하는 라인간 계측시스템의 동일성 검정은 필수적이다. 일반적인 두 집단의 동일성검정 방법은 동일시료를 두 집단에서 반복 측정하여 측정값의 차이를 비교하는 방법이다. 그러나, 반도체 계측특성은 동일시료를 반복 측정할 때, 물리적 영향 등에 의해 시료가 변화하여 반복측정이 난해한 특징을 가지고 있어 일반적인 반복측정 방식의 동일성 검정방법은 적합하지 않다. 본 연구에서는 반복측정이 난해한 반도체 계측 특성 하에서 가설검정을 이용한 라인간 계측 동일성 검정방법을 제시하고 실제 반도체 공정에 적용한 사례를 소개하고자 한다.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.765-774
• /
• 1997

본 논문에서는 반복이 없는 이원배치에서 교호작용의 존재를 가정하고 처리수준간의 모집단 분포의 동일성을 검정하는 비모수적 검정법을 제안하였다. 검정통계량의 구성을 위하여 순위벡터를 그 구조의 형태별로 정리한 순위위치벡터를 제안하고, 이의 특성과 응용가능성을 연구하였다. 또한 모의 검정력 연구를 통하여 기존의 비모수적 방법이 갖는 약점과 제안한 통계량의 우수함을 실증하였다.

• The Korean Journal of Applied Statistics
• /
• v.30 no.4
• /
• pp.513-528
• /
• 2017

Statistics are often used to test two samples if they have been drawn from the same underlying distribution. In this paper, we introduce several well-known distribution-free tests to compare distributions and conduct an extensive Monte-Carlo simulation to specify their behaviors. We consider various circumstances of when two distributions vary in (1) location, (2) scale, (3) symmetry, (4) kurtosis, (5) tail weight. A practical guideline for two-sample goodness-of-fit test is presented based on the simulation result.

• Communications for Statistical Applications and Methods
• /
• v.18 no.2
• /
• pp.219-227
• /
• 2011

In this paper, we proposed a generalized bivariate negative binomial distribution allowing heterogeneous dispersions on two dependent variables based on a trivariate reduction technique. In this model, we propose the score and LR tests for testing the equality of dispersions and compare the efficiencies of the proposed tests using a Monte Carlo study. The Monte Carlo study shows that the proposed score and LR tests prove to be an efficient test for the equality of dispersions in the view of the significance level and power. However, the score test is easier to compute than the LR test and it shows a slightly better performance than the LR test from the Monte Carlo study, we suggest the use of score tests for testing the equality of dispersions on two dependent variables. In addition, an empirical example is provided to illustrate the results.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.3
• /
• pp.569-580
• /
• 2015

Log-rank is widely used for testing equality of two survival functions, and this method is efficient only under the proportional hazard assumption. However, crossing survival functions are common in practice. Therefore, many approaches have been suggested to test equality of them. This study considered several methods; Renyi type test, modified Kolmogorov-Smirnov and Cramer-von Mises test, and weighted Log-rank test, which can be applied when the survival functions cross, and simulated power of those methods. Based on the simulation results, we provide the useful information to choose a suitable approach in a given situation.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.261-272
• /
• 2009

Kolmogorov-Smirnov (K-S) statistic has been widely used for testing homogeneity of two distributions in the credit rating models. Joseph (2005) used K-S statistic to obtain validation criteria which is most well-known. There are other homogeneity test statistics such as the Cramer-von Mises, Anderson-Darling, and Watson statistics. In this paper, these statistics are introduced and applied to obtain criterion of these statistics by extending Joseph (2005)'s work. Another set of alternative criterion is suggested according to various sample sizes, type a error rates, and the ratios of bads and goods by using the simulated data under the similar situation as real credit rating data. We compare and explore among Joseph's criteria and two sets of the proposed criterion and discuss their applications.

• Communications for Statistical Applications and Methods
• /
• v.4 no.2
• /
• pp.557-563
• /
• 1997

Marshall-Olkin의 이변량 지수모형을 따르는 두개의 부품으로 이루어진 시스템에서, 두 부품의 수명들이 이변량 1종 중단된 자료로 관찰되는 경우, 모수에 대한 최우추정량을 구한다. 그리고 두 부품의 수명에 대한 근사적 독립성과 동일성 검정법을 제안하고 몬테칼로 모의실험을 통하여 검정력을 비교하였다.

• The Korean Journal of Applied Statistics
• /
• v.11 no.1
• /
• pp.113-127
• /
• 1998

There have been a great deal of interests in comparing two survival distributins in clinical trials. This paper compares some well-known statistical methods for testing the equality of two survival distributions. Simulation studies also provide some insights into the properties of these test statistics across several types of survival distributions and degrees of censorship.

• The Korean Journal of Applied Statistics
• /
• v.27 no.1
• /
• pp.1-11
• /
• 2014

The Weighted Logrank test and its special case, Logrank test are widely used to compare survival distributions; however, these methods are inappropriate when the sample size is small or censoring distributions are not equal since they use test statistics from approximate distributions. A permutation test can be an alternative for small sample cases; however, this should be used only when censoring distributions are equal. To handle cases with small sample size and unequal censoring distributions, the permutation-imputation method was developed to compare two survival distributions. In this paper, approximate method, permutation method and permutation-imputation method were compared using a Logrank test and Prentice-Wilcoxon test for three or more survival distributions comparison.

• Communications for Statistical Applications and Methods
• /
• v.4 no.2
• /
• pp.549-556
• /
• 1997

본 논문에서는 Block과 Basu (1974)가 제안한 절대연속이변량지수분포(absolutely continuous bivariate exponential distribution : ACBVED)의 독립성검정에 대한 Score검정과 이 검정의 점근성을 높이기 위하여 Cordeiro와 Ferrari (1991)가 제시한 Bartlett수정항과 유사한 형태의 수정된 Score검정을 유도하였다. 그리고 수정된 Score검정의 점근성의 효과와 주변분포가 동일하다는 가정하에서 Gupta, Mehrotra와 Michalek (1984)가 제안한 우도비검정을 모의실험으로 비교하였다.