• 대한안전경영과학회지
• /
• 제16권3호
• /
• pp.267-271
• /
• 2014

The objectives of this study were to evaluate the safe criteria of portable slipmeter using human perception onto the several different floor surfaces under contaminated conditions. It was difficult to find why many different slipmeters took there's own safe criteria. It is still unclear how thres hold values established in many literatures. Two different subjective slippery evaluating methods, AHP(Analytic Hierarchy Process) and Friedman test,were used to evaluate the perception of slipperiness of seven different floor surfaces under the contaminated condition with detergent solution. Twelve subjects worn same footwear and walked with self-selected step and cadence along the test floors. The SCOF(Static Coefficient of Friction) obtained for same test conditions with BOT-3000 was compared to perception of slipperiness to establish as a safe criteria. The very high significant correlation(r=0.97) was found between AHP and Friedman test. Also, The high significant correlation(r=0.96) was found between AHP and SCOF obtained with BOT-3000. The results suggested that the SCOF should be greater than 0.63 for safer walking. Perception rating obtained with AHP showed a high correlation with Friedman test and the SCOF obtained with BOT-3000 except for polished tile floor. The safe criteria obtained through this study were similar to ANSI/NFSIB101.1.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2008년도 춘계학술대회
• /
• pp.451-460
• /
• 2008

This paper reviews nonparametric statistics by Neyman-Pearson test and Fisher test. Nonparametric statistics deal with the small sample with distribution-free assumption in multi-product and small-volume production. Two tests for various nonparametric statistic methods such as sign test, Wilcoxon test, Mann-Whitney test, Kruskal-Wallis test, Mood test, Friedman test and run test are also presented with the steps for testing hypotheses and test of significance.

• 천문학회보
• /
• 제27권1호
• /
• pp.33-33
• /
• 2002

• Communications for Statistical Applications and Methods
• /
• 제9권3호
• /
• pp.607-618
• /
• 2002

Crossover design is often used in clinical trials about chronic diseases like hypertension, asthma and arthritis. In this paper, we suggest nonparametric approaches of Friedman-type rank test based on Bernard-van Elteren test and of aligned method keeping the information of blocks based on the AB/BA/AA/BB crossover design. The simulation results are presented to compare experimental error and power of several methods.

• 대한한의학회지
• /
• 제30권1호
• /
• pp.76-82
• /
• 2009

Objectives: Ryodoraku diagnosis has been used frequently since Nakatani invented it in 1950. There are many papers about how to use Ryodoraku diagnosis in many diseases, but there are no studies about the repeatability and reproducibility of the Ryodoraku score. The aim of this study was to investigate the repeatability and reproducibility of the Ryodoraku score. Materials and Methods: There were four examiners who trained for more than a month, and the number of subjects was twenty. Each of the examiners made Ryodoraku diagnosis for ten subjects three times. We analyzed data by SPSS, used Friedman test, Wilcoxon signer rank test and Spearman correlation test. Results: 1. There was no significant difference between first, second, and third Ryodoraku score by Friedman test in examiners A, B, C, and D, so there was repeatability. 2. There was very high correlation on first, second, third Ryodoraku score by Spearman correlation test in examiners A, B, C, and 0, so there was repeatability. 3. There was high ICC among Ryodoraku score by examiners B, C, and D, so there was reproducibility. 4. After observing four examiners' Ryodoraku diagnoses, we could see the discord of measure points, the amount of hydration before examination, the amount of pressure, examination time, or positions of subjects diagnosed with Ryodoraku incorrectly. Conclusion: There is repeatability and reproducibility of Ryodoraku diagnosis. However, it is still important that one examiner carry out the diagnosis if possible. When there are two or more examiners, they should train extensively and follow manuals.

• Journal of Acupuncture Research
• /
• 제30권3호
• /
• pp.135-140
• /
• 2013

Objectives : The purpose of this study is to investigate the repeatability and reproducibility of the Ryodoraku acupuncture device. For such device to be accepted as a good apparatus for clinical diagnosis, the score it provides should be stable no matter who measure it or when it is measured, assuming all other conditions equal. Materials and Methods : Three oriental medical doctors who were well trained and fully aware of the usage of the Ryodoraku acupuncture device examined ten randomly selected patients three times. Each doctor measured the Ryodoraku scores three times from each of the 10 selected patients. Three doctors were involved in this experiment to investigate the reproducibility and each of them measured the Ryodoraku scores three times from each patient to investigate the repeatability. Data was analyzed with Friedman test, Spearman correlation test, and intra-class correlation coefficient(ICC) in SPSS ver. 18. Results : 1. The Friedman test showed that there is no statistically significant difference between the 1st, 2nd and 3rd Ryodoraku scores measured by the same examiner. It indicates that the Ryodoraku acupuncture device provides the repeatability. 2. Spearman correlation test confirmed the results obtained by the Fiedman test by showing that there exists a strong positive correlation between the three Ryodoraku scores measured by the same examiner. 3. A very high ICC among the three examiner assured that the Ryodoraku acupuncture device achieves the reproducibility. Conclusions : The Ryodoraku acupuncture device achieves the repeatability and reproducibility. However, we still recommend that a doctor trained to a certain level use the Device to carry out the diagnosis. Also, to improve the device in terms of Reproducibility even more, it should be considered to provide a manual for the exact usage.

• 자원ㆍ환경경제연구
• /
• 제23권2호
• /
• pp.187-224
• /
• 2014

본 연구에서는 담합의 경제분석에서 고려해야 할 쟁점들을 논의한 후, 이러한 쟁점들을 반영한 방법론을 특정 수송용 연료시장의 분석에 적용하였다. 가상 경쟁가격과 과잉징수를 산정하는 5가지 방법 중 표준시장비교방법에 기반한 회귀분석방법이 최선이다. 수송용 연료시장에서와 같이 국제가격과 환율이 국내가격에 영향을 미치는 제품의 실거래가격을 분석하는 경우 논리에 부합하면서 유연한 함수형태는 로그-로그 함수형태이다. 경제분석의 대상이 되는 자료가 시계열자료인 경우에 ARDL 모형을 시장별 회귀분석모형의 근간으로 채택하는 것이 필요하며, 표준시장비교방법에 기반한 회귀분석방법에서는 구성 회귀식 간에 모수제약이 포함된 ARDL 회귀식 체계를 구축하고 system FGLS로 추정하여야 한다. Friedman 동질성 검정을 통하여 표준시장 여부를 판별할 수 있다. 통계적 유의성은 불확실성 하에서 입증하고자 하는 명제를 확립하는데 요구되는 최소의 요건이다. 담합관련 소송의 경제분석에서는 민감도 분석은 그다지 유용성이 없으며, 최적모형 선별과정이 더 중요한 절차이다. 위 방법론을 특정 수송용 연료시장의 분석에 적용한 결과, 해당 시장에서는 담합에 기인하는 손해액이 없다는 귀무가설을 기각할 수 없었다.

• 응용통계연구
• /
• 제29권7호
• /
• pp.1411-1419
• /
• 2016

랜덤화 블록 계획법을 검정하는 비모수적 방법에는 일반적인 대립가설에서 Friedman (1937)이 제안한 검정법이 있다. 이 방법은 처리 효과의 차이를 알아보기 위한 검정법으로 블록 내 순위를 사용해 검정함으로써 블록 간 정보의 손실이 있을 수 있다. 본 논문에서는 Hodges와 Lehmann (1962)이 제안한 정렬방법을 이용하여 블록 간 정보 손실을 줄이고, Jo와 Kim (2013)이 제안한 랜덤화 블록 계획법의 결합위치 방법을 확장하여 결합위치에 점수함수를 적용한 새로운 비모수적 방법을 제시하였다. 또한 Monte carlo simulation을 통하여 기존의 검정 방법과 제안한 검정법의 검정력을 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권1호
• /
• pp.95-103
• /
• 2013

랜덤화 블록 모형에서 처리 간의 차이 유무를 검정하는 비모수 방법은 일반 대립가설에서는 Friedman (1937)이, 순서 대립가설에서는 Page (1963)가 제안한 검정법이 있다. 이 방법은 각 블록 내 처리 간의 순위를 이용하여 처리 간의 차이를 검정하는 검정법이다. 본 논문에서는 Hodges와 Lehmann (1962)의 정렬 방법과 Chung과 Kim (2007)이 제안한 결합위치 검정법을 확장하여 랜덤화 블록 모형에서 새로운 비모수적 방법을 제시하였다. 또한, 모의실험을 통하여 모수적 방법과 기존의 비모수적 방법과의 검정력을 비교하였다.

• 응용통계연구
• /
• 제29권4호
• /
• pp.707-717
• /
• 2016

랜덤화 블록 계획법을 검정하는 비모수 방법은 일반 대립가설에서 Friedman (1937), 순서형 대립가설에서 Page (1963)가 제안한 방법이 있다. 이 방법은 각 블록 내 처리 간 순위를 이용해 처리 간의 차이를 검정하는 방법이다. 본 논문에서는 Hodges와 Lehmann (1962)이 제안한 정렬방법을 이용하여 블록 간 정보의 손실을 줄이고, Orban과 Wolfe (1982)가 제안한 위치를 확장하여, Kim (1999)이 제안한 대조군과 처리군의 방법을 이용하여 랜덤화 블록 모형에서 새로운 비모수 검정 방법을 제안하였다. 또한 Monte Carlo 모의실험을 통해 제안방법과 기존의 검정 방법을 비교하였다.