• 응용통계연구
• /
• 제27권1호
• /
• pp.61-70
• /
• 2014

랜덤화 블록 계획법은 동질적인 실험단위를 묶어 여러 개의 블록으로 나눈 후, 각 블록의 실험단위에 처리를 적용하는 방법이다. 랜덤화 블록 계획법에서 Jonkckheere (1964)와 Terpstra (1952), Page (1963) 그리고 Hollander (1967) 등이 순서대립가설의 다양한 방법을 제안하였다. 특히, 블록 내 순위합의 가중치를 주는 방법으로 Page (1963) 검정법이 있다. 본 논문에서는 Page 검정을 확장하여 순서대립가설에 새로운 비모수적 방법론을 제안하였다. 또한, 몬테카를로 모의시험 연구를 통해 제안된 방법과 이전의 방법들의 검정력을 비교하였다.

• 한국ITS학회 논문지
• /
• 제8권2호
• /
• pp.108-117
• /
• 2009

현재 우리나라에서는 자전거 이용 활성화를 통해 교통문제를 해소하며, 고유가 시대의 에너지 절약 효과를 얻고자 하고 있다. 그러나, 자전거 인프라 시설의 부족 및 기존 자전거 도로 및 관련시설의 안전성과 연계성이 보장되지 않는 등의 이유로 자전거 이용이 불편한 실정이다. 따라서 본 연구에서는 안전성, 편의성, 연계성 등의 다양한 영향요소들을 고려하여 이용자 중심의 자전거 서비스 수준(BLOS: Bicyclist Level of Service) 모형을 개발함으로써 기존 자전거 도로 및 시설의 서비스 수준을 정의하고 개선하는데 기여하고자 하였다. 또한, 순차적 의미를 주는 선택, 선호, 강도 등에 관련된 연구에 적합한 순서형 프로빗 모형(Ordered Probit Model)을 적용함으로써, 자전거 이용자의 만족도를 고려한 자전거 서비스 수준 평가 기준을 제시하고자 한다. 본 연구에서 개발한 모형을 통해 자전거 서비스 수준 평가를 수행함으로써 기존의 자전거 도로 및 시설을 이용자 관점에 맞도록 개선할 수 있으며, 이러한 과정을 통해 자전거 시설 이용 증진을 도모할 수 있겠다. 또한, 자전거 도로망 계획, 자전거 도로 설계, 개선 효과에 따른 자전거 도로 및 시설의 투자 우선순위 결정 등에 활용될 것으로 기대된다.

• 응용통계연구
• /
• 제29권7호
• /
• pp.1399-1409
• /
• 2016

랜덤화 블록 계획법(randomized block design)에서 대립가설형태에 따라 많은 비모수적인 방법들이 제안되었다. 일반대립가설에서 대표적으로 Fridman (1937)의 검정법이 있고, 순서형 대립가설에서는 Page (1963)의 검정법이 있다. 우산형 대립가설에 대한 비모수적 방법으로는 일원 배치 모형에서 k개의 표본 문제에 대하여 Mack과 Wolfe (1981)의 검정법이 있다. 본 논문에서는 랜덤화 블록 계획법(randomized block design)에서 우산형대립가설에 대하여 블록 간의 정보를 이용한 Hodges와 Lehmann (1962)의 정렬방법과 위치를 이용한 Kim (1999)의 검정법을 이용하여 검정법을 제안하였다. 또한, Monte carlo 모의실험을 통하여 제안된 검정법과 기존의 검정법을 비교하였다.

• 산업경영시스템학회지
• /
• 제18권34호
• /
• pp.1-8
• /
• 1995

The practical problem of multi-attribute decision making are formed by the uncertain attribute that the attribute by the alternatives cannot be defined or judged crisphy but only as vague. In this case the final judgements are also represented by vague which have to be ordered to determine the optimal alternative. The problem is more complex if the evaluations of alternatives according to each attribute are expresed vague. This paper described the results of a study done to determine how well multi-attribute decision marking perform in helping a decision maker arrive at a preferred solution to a multi-attribute problem with vague attribute. Particular area of research has concentrated on the issue of combining quantitative and qualitative data supplied by estimation. Futher study considers some method for suitable evaluation of qualitative data.

• ETRI Journal
• /
• 제28권2호
• /
• pp.205-215
• /
• 2006

Wireless data communication (WDC) services are increasingly penetrating the market. The two main alternative WDC technologies are wireless LAN and mobile Internet. Services based on these technologies display differences in quality attributes such as terminal device, data transmission speed, pricing scheme and so on. How consumers choose between these two alternatives will be determined by their preferences regarding such quality attributes. In turn, their preferences will affect the evolution of WDC services and related technologies. This study employs a conjoint analysis of consumer valuations of quality attributes of wireless LAN and mobile Internet services. Respondents rate hypothetical service alternatives featuring various combinations of quality attributes. By estimating consumer willingness to pay for the attributes of WDC services, the authors predict the evolution of WDC services and related technologies along various quality dimensions, make a comparison with the results of a previous study, and draw policy implications for national-and company-level R&D strategies.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제20권2호
• /
• pp.109-116
• /
• 2013

In this paper, we propose a Jonckheere type test statistic for testing the parallelism of k regression lines against ordered alternatives. The order restriction problems could arise in various settings such as location, scale, and regression problems. But most of theory about the statistical inferences under order restrictions has been developed to deal with location parameters. The proposed test is an application of Jonckheere's procedure to regression problem. Asymptotic normality and asymptotic distribution-free properties of the test statistic are obtained under some regularity conditions.

• 농업과학연구
• /
• 제30권2호
• /
• pp.139-147
• /
• 2003

The main purpose of this study is to obtain forest scenic beauty management informations toward forest working systems in pinus densiflora forest stands, etc. To get these information, visual preference and spatial image analysis methods are used. 25 different alternatives were simulated to visualize on basis of actual forest working methods with taken photos from May to July, 2003. The options were illustrated as photos produced by computer software. Respondents' ratings for 25 landscape scenes were obtained by interview survey method. Each alternatives were evaluated by forest major student group with total 103 respondents after reliability test. Visual preference evaluation was used 10 point rating scale. Spatial images of 12 alternatives were measured by 12 semantic differential scale. In general, the respondents preferred refreshing and ordering forest stand after forest working to natural forest stand before forest working. High visual preference for forest density produces 400-600 trees/ha in small diameter class forest stands. Regarding visual preference according to pavement type of trail, soil trail is ranked high. Visual preference for cutting area ranks mature forest stand and visual preference for trail slope cover type ranks shrub with grass as relatively high on the preference scale. Through the factor analysis, spatial images of 12 coniferous forest stands are classified as 'ordered opened' and 'beautiful healthy'. Results indicate how to conduct forest working systems for forest scenic beauty management.

• 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.

• 농업과학연구
• /
• 제27권1호
• /
• pp.5-12
• /
• 2000

The main purpose of this study is to obtain spatial image information toward forest thinning process in Larix forest stands. Thirteen different alternatives were simulated to visualize on the basis of actual thinning work photos. The options were illustrated as photos produced by photoshop program. Each alternatives were evaluated by forest visitor group with total 244 respondents after reliability test. Spatial images of 13 thinning photos were measured by 12 semantic differential scale as broad -narrow, ordered-tangled, friendly-unfriendly, monotonous-divers, dry-refreshing, relieved -stifling, healthy-sickly, uniform-scattered, dead-alive, opened-closed, bent-straight, and beautiful-ugly. In comparison with thinning stands and natural stands, thinning works were visual improvement effects of spatial images. Seemingly, this trend is due to definite form beauty, straight and clear length form of coniferous forest, As can be expected, slash and downwood were negatively related to improvement effects of spatial images. The 60% ratio of stem/ tree height and 450-950 trees/ha was positive in attraction of spatial images. Results indicate how to conduct forest thinning system for spatial images on Larix forest stands.

• 산업경영시스템학회지
• /
• 제23권54호
• /
• pp.87-95
• /
• 2000

To constuct the stochastic model for performance evaluation of Multi-AGV, two aspects must be considered. The first is stochastic situation for moving jobs. The second is the dispatching rule of AGV. In this paper, the stochastic model for performance evaluation of Multi-AGV is developed. The case of stochastic model with two AGV is developed. But it difficult to solve in the case of stochastic model with more than three AGV because the model have three-ordered equations. The evaluation factor of the model is utilization and empty travel time of AGV. Using these factors, one can easily evaluate a wide range of handling and layout alternatives from given flow data. Hence, the model would be most effective when used in the early stage of designing to narrow down the number of alternative prior to simuation.