• 자원ㆍ환경경제연구
• /
• 제11권1호
• /
• pp.99-119
• /
• 2002

As an alternative to classical maximum likelihood approach for analyzing dichotomous choice contingent valuation (DCCV) data, this paper develops a Bayesian approach. By using the idea of Gibbs sampling and data augmentation, the approach enables one to perform exact inference for DCCV models. A by-product from the approach is welfare measure, such as the mean willingness to pay, and its confidence interval, which can be used for policy analysis. The efficacy of the approach relative to the classical approach is discussed in the context of empirical DCCV studies. It is concluded that there appears to be considerable scope for the use of the Bayesian analysis in dealing with DCCV data.

• 한국과학교육학회지
• /
• 제24권1호
• /
• pp.17-28
• /
• 2004

The purpose of this study is to determine the patterns of differences between genders in science achievement. Eleventh grade, 140 female and male students were sampled from a school in Seoul. According to the analysis results of pilot study, 20 items were finally selected for the main study. To sharpen our interpretations of the factors and provide some confirmation, we supplemented the statistical analysis with a more detailed cognitive study of the items using think-aloud protocols and interviews with student test takers. The analysis of this study took into account the different item formats, contexts, and presentation styles. The findings are as follows: First, there was no significant gender difference between multiple-choice and open-ended items. Second, male students achieved significantly better in the context of everyday life in multiple-choice items. Third, male students favored items presented as written texts. Fourth, in problem-solving process, female students tend to apply their science concepts, whereas male students tend to apply their everyday experiences. The results of this investigation indicate that gender difference in science achievement depends heavily on item characteristics.

• Animal cells and systems
• /
• 제8권2호
• /
• pp.81-87
• /
• 2004

Male red-spotted newts, Notophthalmus viridescens, use chemical cues to locate and select potential mates. To investigate whether large and small males respond differentially to chemical cues from conspecifics, we conducted a series of two-choice Y-maze tests with odorant stimuli from two large females (LF/LF), one large versus one small female (LF/SF), and one large female placed with four males versus one small female (LF+4M/SF). We found that males responded more rapidly in a LF/LF choice situation than in those involving LF/SF or LF+4M/SF. In addition, small males chose more quickly than did large males. These results suggest that both body size and odorant context affect the speed of odorant responses. By responding differentially to conspecific chemical cues, small males may arrive earlier at a courting area, increasing their chances of successfully guarding and mating with a female.

• Journal of the Korean Data and Information Science Society
• /
• 제21권6호
• /
• pp.1051-1060
• /
• 2010

도금공정에서는 도금두께의 규격한계는 주어지지만 대부분의 경우 목표치는 주어지지 않는다. 목표치가 주어지지 않았을 때 일반적으로 규격의 중심점이 목표치로 사용된다. 하지만 공정능력치가 크다면 규격의 중심을 목표치로 사용하는 것은 총 손실비용면에서 최선의 선택이 아니다. 이 논문에서는 총 손실비용을 생산비용과 손실함수의 합으로 정의하였고 기대 총 손실비용을 최소화 하는 목표치를 제안하였다. 그리고 그때의 공정능력치의 감소가 미미한 것을 보였다.

• 한국항만학회지
• /
• 제8권1호
• /
• pp.49-63
• /
• 1994

The introduction of high speed railway system a significant impact on the conventional inter-urban transport systems by inducing a significant traffic from the existing modes as well as generating a new traffic. It is also closely related to intra-urban transport systems as the inter-urban traffic has its origin and destination in a city. In the context of mode choice, for high speed transport systems, it has been argued that the accessibility is the most important attribute conceived by users. Thus this study attempts to analysis the importance of the accessibility for the planned high speed railway systems particularly with respect to the location of Busan Station. For this Stated-Preference approach, which is considered appropriate for such study, is adopted, and disaggregate binary logit models for mode choice between the high speed railway and air service in Busan-Seoul corridor are developed. The elasticities for cost and service variables are also derived. The results disclose that cost is the most important which is inconsistent with most previous studies ; accessibility has considerable impact on the choice ; and frequency however has a little impacts. Concerning location of the high speed railway station the results suggest that the longer the access distance is, the more important the accessibility is. This implies that the connection of reliable access transport services such as underground are essential between the terminal and urban center.

• 동아시아식생활학회지
• /
• 제24권6호
• /
• pp.915-923
• /
• 2014

This study investigated organic coffee choice motives from a coffee shop market segmentation perspective in order to understand the potential importance they may have upon attitudes and behavioral intentions to buy organic coffee. A factor-cluster segmentation approach was used for this study. An exploratory factor analysis identified five organic coffee choice motives: 'Sensory', 'Environment', 'Trust', 'Health' and 'Price'. Based upon these five choice motives, cluster analyses classified all respondents into three homogeneous subgroups: 'Highly motivated', 'Moderately motivated' and 'Unmotivated'. Analysis of variance tests indicated that attitudes and intentions to purchase organic coffee were significantly different among the three clusters. In particular, two cluster groups representing 'Highly motivated' and 'Moderately motivated' were found to offer the most utility for further organic coffee market segmentation research. Especially, due to perceptions about high price premium of organic coffee, the 'Moderately motivated' group had higher positive attitudes, although, their intentions to buy organic coffee were not higher than those of the 'Unmotivated' cluster. Findings support previous research propositions that high price could be the strongest barrier for people to purchase organic products including the organic coffee business context. This will assist to market and promote pricing strategies for caf$\acute{e}$s and restaurants to optimize organic coffee sales revenue. Implications for all cluster groups regarding unique socio-demographic characteristics and behavioral intentions are discussed. Organic coffee marketers can apply these findings towards the development of effective target market strategies.

• Communications for Statistical Applications and Methods
• /
• 제15권4호
• /
• pp.543-549
• /
• 2008

Inspired by using a robust loss function in the support vector machine regression to control training error and the idea of robust template matching with M-estimator, Chen (2004) applies M-estimator techniques to gaussian radial basis functions and form a new class of robust kernels for the support vector machines. We are specially interested in the shape of the Huber's M-estimator in this context and propose a way to find the shape parameter of the Huber's M-estimating function. For simplicity, only the two-class classification problem is considered.

• Asia Marketing Journal
• /
• 제19권1호
• /
• pp.35-54
• /
• 2017

Researchers in marketing, sociology, and economics have been interested in the role of social interactions in consumer choice and consumption behaviors. Social interactions, labeled variously as peer effects, social contagion, and neighborhood effects, have important implications for firms' allocation of marketing efforts. In this research, we test and provide empirical evidence for peer effects in consumers' service usage in the context of gym-going behaviors. Using a detailed individual-level membership and attendance data at one of the largest health club chains in the U.S., we document that a focal member's gym-going behavior is influenced by the behaviors and characteristics of the peers at the same branch

• 지능정보연구
• /
• 제14권2호
• /
• pp.1-20
• /
• 2008

정보기술의 급격한 발전은 경영환경에서 다양한 정보를 산출하여 의사결정자들이 의사결정을 효과적으로 지원할 수 있는 수단을 요구하고 있다. 특히 유비쿼터스 환경의 등장으로 이러한 의사결정형태는 더욱 복잡해지고 다양해 질것으로 기대된다. 이에 본 연구에서는 유비쿼터스 환경에서의 의사결정지원시스템(UDSS：Ubiquitous Decision Support Systems)이 실제 업무에서 의사결정과정과 의사결정의 성과에 어떠한 영향을 미치는지 실증적으로 분석하고자 하였다. 이를 위해 모바일 택배 시스템(MDS：Mobile Delivery System)을 UDSS로 간주하고 유비쿼터스 환경의 주요한 두 속성인 유비쿼터스 접속성과 상황인식기능이 의사결정자의 의사결정과정과 성과에 어떠한 영향을 미치는지 실증자료를 이용하여 분석하였다. 분석결과 유비쿼터스 접속성은 의사결정과정에서 대안설계에 유의한 영향을 미치지 못하였으나, 상황인식기능은 의사결정의 모든 과정에 유의한 영향을 미치는 것으로 나타났다. 한편, 의사결정과정 간의 각 단계들은 상호 유의한 인과관계를 나타냈으며, 의사결정과정과 의사결정의 성과는 모두 유의한 것으로 나타났다. 이러한 결과를 바탕으로 향후 UDSS의 설계 및 구현에 필요한 시사점 및 향후 연구방향을 제시하였다.

• 경영정보학연구
• /
• 제8권1호
• /
• pp.159-179
• /
• 2006

정보통신 기술의 발달과 IT 아웃소싱의 확대로 인터넷접속 서비스, 응용프로그램 서비스, 컨텐츠 서비스, 저장 서비스 등 다양한 종류의 가입형 정보통신 서비스가 제공되고 있다. 시장의 성숙과 산업 간 융합에 따른 경쟁의 심화로 인하여, 이들 서비스 제공기업들에게 있어서 기존 고객을 유지하고 경쟁사 고객의 전환을 유도하기 위한 고객 관리가 중요한 과제가 되고 있다. 본 연구에서는 가입형 정보통신 서비스 제공 기업들의 효과적인 고객 관리를 위하여, 서비스 구매 후의 고객 선택(기존 서비스의 계속적 이용 또는 다른 서비스로의 전환)에 영향을 미치는 요인들을 영향의 주체와 영향의 성격에 따라 Holding 요인, Defect 요인, Inducement 요인, Hurdle 요인으로 유형화하고 이를 바탕으로 가입형 정보통신 서비스의 구매 후 고객선택모형을 제시하였다. 또한, 제시된 모형의 활용 방안을 초고속 인터넷 서비스를 중심으로 제시하였다. 이러한 고객선택모형의 활용은 기술의 급속한 발전과 다양한 대체 서비스의 출현으로 빠른 수명 주기를 보이는 가입형 정보통신 서비스 시장에서 효과적인 고객 관리를 통한 경쟁 우위의 확보에 기여할 수 있을 것이다.