• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.237-249
• /
• 1999

It has been issued that the irreconcilability of the classical test for a point null and standard Bayesian formulation for testing such a point null. The infimum of the posterior probability of the null hypothesis is used as measure of evidence against the null hypothesis in Bayesian approach; here the infimum is over the family of priors on the alternative hypotheses which includes all density that are a priori reasonable. For iid observations from a multivariate normal distribution in $\textit{p}$ dimensions with an unknown mean and a covariance matrix propotional to the Identity we consider the difference and the Wolfowitz distance of the distributions of the P-value and the lower bound of the posterior probability over the family of all normal priors. The Wolfowitz distance is interpreted as the average difference of the quantiles of the two distrbutions.

• Journal of the Korean Statistical Society
• /
• 제25권3호
• /
• pp.337-346
• /
• 1996

The chi-squared type statistic generated from the empirical process can be used for testing the goodness of fit hypothesis on iid random sample. Lee (1995) showed that under some conditions, the chi-squared type statistic is asymptotically maximin in the sense of Strasser (1985). Since the chi-squared type statistic depends on the choice of *points in the unit interval, it is worth investigating the points yielding more efficient tests. Motivated by this viewpoint, we are led to study the asymptotic relative efficiency of chi-squared type tests in the same setting of Lee (1995). Some examples are given for illustration.

• Journal of Communications and Networks
• /
• 제14권5호
• /
• pp.481-486
• /
• 2012

Accurate and efficient estimation of the number of sources is critical for providing the parameter of targets in problems of array signal processing and blind source separation among other such problems. When conventional estimators work in unfavorable scenarios, e.g., at low signal-to-noise ratio (SNR), with a small number of snapshots, or for sources with a different strength, it is challenging to maintain good performance. In this paper, the detection limit of the minimum description length (MDL) estimator and the signal strength required for reliable detection are first discussed. Though a comparison, we analyze the reason that performances of classical estimators deteriorate completely in unfavorable scenarios. After discussing the limiting distribution of eigenvalues of the sample covariance matrix, we propose a new approach for estimating the number of sources which is based on a sequential hypothesis test. The new estimator performs better in unfavorable scenarios and is consistent in the traditional asymptotic sense. Finally, numerical evaluations indicate that the proposed estimator performs well when compared with other traditional estimators at low SNR and in the finite sample size case, especially when weak signals are superimposed on the strong signals.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.1
• /
• pp.35-40
• /
• 2006

For the maritime traffic safety assessment of vessels navigating in harbor or fairway, simulation techniques by using shiphandling simulator system have been traditionally used. When designing the simulation experiments and when analyzing the simulation results, however, there has been a little systematic method. Ship-handling simulations can be regarded as a kind of statistical experiment by using ship-handling simulator system, which means that shiphandling simulation conditions should be designed statistically and that the simulation results should be statistically analyzed as well. For the safe and economic design of harbor and fairway, reasonable decisions based upon the scientific analysis of shiphandling simulation results are indispensable. In this paper, various statistical methods, such as Bayes theorem, statistical hypothesis testing, and probability distributions, are reviewed with a view to application to maritime traffic safety assessment. It is expected that more reasonable decisions on harbor and fairway design can be made from shiphandlers' view point by using statistical methods.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권1호
• /
• pp.419-430
• /
• 2021

The study aims to analyze the factors that shape patient loyalty, namely, by involving the service quality factor (SERVQUAL), hospital image, patient value, and patient satisfaction in private hospitals. This study was conducted in Makassar City, Indonesia, with a sample of 296 eligible samples from private hospitals. The sample criteria were patients with outpatient and hospitalization status. Then, this study developed 23 hypotheses to test the statistical relationship between direct, intervening and multiple-effect models. Problem-solving and research focus are carried out using a quantitative method approach with a PLS-SEM-based testing tool. The bootstrapping method is being used with the constant bootstrapping step to demonstrate the results of hypothesis testing; we find that the overall hypothesis has a positive and significant effect. The combination of testing models involving several variables shows that a patient's loyalty can be formed if a patient's satisfaction has been realized. Satisfaction can be realized if the value-customer has been felt by the patients. Therefore, the hospital image must be directly proportional to service quality. Service quality is the essence of service that directly affects customers; service quality is also the reason that shapes consumer perceptions in increasing rationalization and solid customer (patient's) decision-making.

• 응용통계연구
• /
• 제21권5호
• /
• pp.867-873
• /
• 2008

임상시험의 자료에 대하여 통계적 검정을 실시하는 경우 유의수준 5%를 사용하는 것이 관례이다. 하지만 동등성 시험을 신뢰구간을 사용하여 검정하는 경우, 신뢰도 90%인 신뢰구간이 사용되고 있다. 흔히 신뢰도 $1-{\alpha}$인 신뢰구간을 검정에 사용하는 경우, 그 검정법의 유의수준은 ${\alpha}$이다. 이 때문에 동등성 검정에서 신뢰도 90%인 신뢰구간을 사용하게 되면, 유의수준은 10%가 되는 것이 아닌가 하는 혼란을 일으켰다. 본 논문에서는 이와 관련된 이슈들을 관련 문헌의 검토와 시뮬레이션을 통하여 명확하게 하여, 제약회사, CRO, 대학병원 등에 종사하는 통계전문가들에게 도움을 주고자 한다.

• 감성과학
• /
• 제20권2호
• /
• pp.149-160
• /
• 2017

가설검증 과정에서 자료 분석 결과 산출된 통계치에 대한 해석은 몇 가지 통계학적 이론을 토대로 분석 결과 산출된 관련 통계치의 이론적 확률 분포에 의해 좌우된다. 예를 들어 실험 조건 간 측정치의 평균 차이에 대한 통계적 유의미성은 대개 전집 특성에 대한 몇 가지 이론적 가정에 기초해 구성된 해당 평균 차이값의 확률 분포(예: Student's t)에 기초해 결정된다. 본 연구는 이러한 이론적 통계치의 분포가 아닌 실측정 자료의 무선 재구성을 통해 얻어진 경험적 통계치의 분포에 기초해 가설 검증을 시도하는 무선재추출법의 기본 논리와 장점을 살펴보고 사건관련전위 분석 상황에서의 응용 가능성을 모색하였다. 더 나아가 무선 추출 원리에 기초한 무선치환법이 적용된 구체적 사례를 소개하고 ERP 자료 분석에 있어서 경험적 통계 분석 적용에 앞서 유의할 점을 살펴봄으로써 뇌파 연구자들의 무선재추출법에 대한 정확한 이해를 도모하였다.

• 한국임상수의학회지
• /
• 제26권3호
• /
• pp.189-199
• /
• 2009

With the growing importance of evidence-based medicine, clinical or biomedical research relies critically on the validity and reliability of data, and the subsequent statistical inferences for medical decision-making may lead to valid conclusion. Despite widespread use of analytical techniques in papers published in the Journal of Veterinary Clinics statistical errors particularly in design of experiments, research methodology or data analysis methods are commonly encountered. These flaws often leading to misinterpretation of the data, thereby, subjected to inappropriate conclusions. This article is the first in a series of nontechnical introduction designed not to systemic review of medical statistics but intended to provide the journal readers with an understanding of common statistical concepts, including data scale, selection of appropriate statistical methods, descriptive statistics, data transformation, confidence interval, the principles of hypothesis testing, sampling distribution, and interpretation of results.

• 응용통계연구
• /
• 제32권1호
• /
• pp.1-13
• /
• 2019

최근에 제안된 심리스(seamless) 제 2상/제 3상 임상시험 디자인은 기존의 임상시험 디자인들과 비교하여 피험자수를 줄일 수 있을 뿐만 아니라 임상 개발 시간을 단축시킬 수 있다는 장점을 가지고 있어 임상시험연구자들의 많은 관심을 끌고 있다. 또한 제 3상 시험을 단독으로 진행 하였을 때보다 더 높은 검정력을 가질 수 있으므로 임상시험에서 매우 효율적이라 말할 수 있다. 본 논문에서는 제 2상에서 최고효과 용량군을 선정하기 위한 여러 가지 다중가설 검정방법들을 제시하고 제 2상에서 최고효과 용량군을 선정한 후에 제 2상과 제 3상을 결합하는 여러 가지 유의확률 결합검정방법들을 제시하였다. 또한 모의실험을 통해서 심리스 제 2상/제 3상 임상설계가 적용되었을 때 여러 가지 방법들을 비교함으로써, 제 2상/제 3상 표본의 크기 조합이나 분산의 크기가 다른 여러 가지 상황에서 가장 적절한 방법을 선택하는 가이드라인을 제시하고자 한다.

• 대한조선학회논문집
• /
• 제53권2호
• /
• pp.127-134
• /
• 2016

This paper presents practical issues for test and evaluation(T&E) methods to develop defense systems. Our argument is motivated by several domestic defense cases and the cases lead us to discuss two main factors for reliable defense systems development: 1) statistical approaches and 2) technical schemes. Specifically, statistical approaches enable to provide credible interpretations about T&E results in the decision-making process. With practical T&E results of the “Red Shark” torpedo, we performed statistical hypothesis tests and suggest a minimum sample size to accept the hypothesis. Next, technical schemes have more direct effects on improving reliability of developed defense systems and we shortly introduce tools development for systems verification that is required to integrate several sub-systems, e.g., combat, sensor, weapon, and communication systems, within a defense system. We additionally summary some domain cases using modeling and simulation techniques for successful T&E. In closing, we expect that the paper shows empirical investigation and lessons learned with these two practical issues, which provides a guide those who desire to make decisions about reliable defense systems development.