• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.1057-1065
• /
• 2010

In this paper we discuss some cautionary notes in using the Pearson chi-squared test statistic for the goodness-of-fit of the ordinal response model. If a model includes continuous type explanatory variables, the resulting table from the t of a model is not a regular one in the sense that the cell boundaries are not fixed but randomly determined by some other criteria. The chi-squared statistic from this kind of table does not have a limiting chi-square distribution in general and we need to be very cautious of the use of a chi-squared type goodness-of-t test. We also study the limiting distribution of the chi-squared type statistic for testing the goodness-of-t of cumulative logit models with ordinal responses. The regularity conditions necessary to the limiting distribution will be reformulated in the framework of the cumulative logit model by modifying those of Moore and Spruill (1975). Due to the complex limiting distribution, a parametric bootstrap testing procedure is a good alternative and we explained the suggested method through a practical example of an ordinal response dataset.

• Journal of the Korea Safety Management & Science
• /
• v.9 no.3
• /
• pp.95-102
• /
• 2007

Nowadays, globally high-grade companies have done their best for increasing their competitive power through a many kinds of method in incisive competition for making certain of a pacesetting position. Among the rest, Six Sigma have been the best methodology of improving process and have proven to be effective by the result of improving process in many of manufacturing business, however, it has not obtained excellent results in the transaction business. In transaction business, a $30\sim50%$ costs in total costs is generated by slow-speed working and reworking. The slow processes decrease the quality and increase the cost, which decreases customer satisfaction, and finally the income is decreased. All of them are so called wastes in processes. For this, adopting of lean six sigma methodology in process management can eliminate the wastes and reduce the variation. This study focuses on distribution with the domains like capacity, layout, amount of location, assignment of product, operation procedure and operation rule in order to improve these domains, we make a further application of eight analysis ways based on DMAIC method for improving operation of processes of distribution center as the third profit source. The goal of this study is to trace an approach that can easily adopt of Lean Six Sigma in operational management of distribution center by a kind of data, analysis method and template.

• Communications for Statistical Applications and Methods
• /
• v.17 no.4
• /
• pp.527-540
• /
• 2010

Rule-based classification analysis is widely used for massive datamining because it is easy to understand and its algorithm is uncomplicated. In this classification analysis, majority vote of rules or weighted combination of rules using their supports are frequently used in order to combine rules. We propose a method to combine rules by using the multinomial distribution in this paper. Iterative proportional fitting algorithm is used to estimate the multinomial distribution which maximizes entropy constrained on rules' support. Simulation experiments show that this method can compete with other well known classification models in the case of two similar populations.

• ALGAE
• /
• v.26 no.1
• /
• pp.41-50
• /
• 2011

Yellow Sea surface sediment samples collected on October 15-31, 2003 were analyzed using the palynological process to investigate the spatial distribution of dinoflagellate resting cysts. The sampling areas comprised four latitudinal transects, the northernmost of which was located off the Shandong Peninsula, China and the southernmost off Jeju Island, Korea. Each transect line was composed of six to nine stations, spanning the distance between the Chinese and Korean coasts. Twenty-five different types of dinoflagellate cysts were identified. Gonyaulax scrippsae, Alexandrium spp. (ellipsoidal type), and G. spinifera were the most dominant at all stations surveyed. Dinoflagellate cysts belonging to the Gonyaulacales comprised over 50% of all cysts collected. The latitudinal distribution trend showed that cyst concentrations along the two middle transects were much higher than those along the two northern and southern transects. Cyst concentrations in the offshore central areas reached their highest values within each transect and gradually decreased toward the Chinese and Korean coasts. Overall, cyst concentrations were markedly elevated in the offshore central Yellow Sea areas and gradually decreased outward in all four directions. This concentric cyst distribution pattern was consistent with the hydrographic features of the Yellow Sea, such as circular current systems, sedimentary properties, and water depth.

• Journal of Distribution Science
• /
• v.16 no.5
• /
• pp.61-70
• /
• 2018

Purpose - These days, an individual user, private entity, hears everyday news of hacking and personal information leakage in the era of a most-connected society. This study investigates cyber attack, cyber insurance and distribution channels for insurance goods in South Korea by analyzing various cases of cyber attacks in domestic and overseas case. Research design, data and methodology - This study adopted various study cases instead of the one large case for deep quality analysis, and focused on various cases of domestic and overseas cyber attacks with insurance. Result - As a result of analyzing the cases that were hacked, types of massive losses and damages arising out of internet blackout due to cyber risks are paralyzation of public and private website and portal, electronic administrative system, public infrastructure, and consequently a normal operation of nation is impossible. These losses and damages however can be coverable under cyber insurance. Conclusions - This paper suggests insurance carriers, as suppliers, should provide multiple channels to sell to the customer and should expand the strategy of advertisement and promotion in order for them to change their mind and compare the price and value of the information of individual users and private entity in view of cost savings.

• Journal of Distribution Science
• /
• v.17 no.6
• /
• pp.57-63
• /
• 2019

Purpose - This research is to review the state of standard labeling compliance and identify the factors that are conducive to compliance with the Labeling Standards of the Health Functional Foods Act in internet distribution. Research design, data, and methodology - We checked 9 labels including product name, expiration date, manufacturing date, raw material, ingredient, operative dose, nutritional information, daily intake, and functional effect which are based on Labeling Standards of the Act from 100 health functional foods in the internet shopping malls. These 9 structure & function claims were compared using a Chi-square test. Results - There was a statistically significant difference in the use of standard labeling between domestic product and imported products (p<.001). The related strength between these two variables showed a moderate effect size. Also, there was a statistically significant difference between accredited advertising/unaccredited advertising distinction and use of standard labeling (p<.001). The related strength between these two variables showed a moderate effect size. Conclusions - The Labeling Standards of the Act were not followed and found to be related to imports or unauthorized advertising in internet distribution. The information displayed according to the Labeling Standards was only about 2 on the average, so many labels have been posted unreadably without arrangement.

• Journal of Distribution Science
• /
• v.17 no.2
• /
• pp.35-42
• /
• 2019

Purpose - There is little research on the market of foreign infant education materials. So, it is needed to deeply examine the development and preference factors of foreign infant education materials. Therefore, this study presents a future method and model for analyzing the important variables of buying foreign infant education materials. Research design, data, and methodology - The conjoint analysis method and model of this paper is used as follows. Conjoint analysis method is possible to derive the attributes to be analyzed through the model of the preferred factors, and then to derive the sub-attributes of the attributes. Results - This study derived preference attributes between brand benefit, equity (brand image, loyalty, awareness), distribution network (department store, specialty stores, discount store, internet mall), and service quality (tangibles, reliability, responsiveness, assurance, empathy) in infant education materials conjoint model. Conclusions - Since the opening of the education market in Korea, parents have a high education level due to low birth rate. The advantages of the conjoint analysis method have been extended to the study of infant education materials. Based on this, this paper will identify important attributes that are considered in preference of foreign infant education materials and help to establish and implement future marketing strategies.

• The Korean Journal of Emergency Medical Services
• /
• v.6 no.1
• /
• pp.55-64
• /
• 2002

This analysis is accomplished by using 331 rescue and medical evacuation cases performed by KangWonDo Fire Service Department Aviation(KFSA-119 Heicopters) between Jan. 1998 and Oct. 2002. By analysing injury causes, annual differences, sexual, scenic(locaional) distribution and wounded part distribution, this study tried to figure out the general tendency of the helicopter-transported patients in Korea. The results are as follows; 1. The whole population of the patients rescued and transported by helicopters is increasing by the annual rate of 150%~200%. 2. For the locational (scenic) distribution of the patients, 57% (190 cases) of the target population were injured on their mountain-climbing or tracking. 3. 12% (41 cases) of the target population were the Inter-Hospital transport cases. 4. 6% (16 cases) were the expired cases. 5. for the wounded part distribution, 46% (106 cases) were muscular skeletal injuries. 6. The aircraft and personnel of the KFSA were rescue-oriented, so for the EMS operations especially inter-hospital transport missions, different medical equipments and personnels are needed.

• Journal of The Korean Astronomical Society
• /
• v.29 no.spc1
• /
• pp.169-170
• /
• 1996

In the past, it. was very difficult to distinguish thermal and non-thermal emission. Broadbent et a1. (1989) has developed a new technique with the help of the IRAS 60 micron emission. The distribution of non-thermal or synchrotron emission in the Galactic disk has been modeled from the 408 MHz all sky survey of Haslam et a1. (1982) after removal of the thermal component.. At. 408 MHz, t.here is very little absorption in the interstellar medium and the distribution along the line-of-sight. is inferred mainly from its presumed relationship to other tracers of spiral structure via a. number of fitted parameters. But. at lower frequencies, free-free absorption becomes important and can give some direct. information on the line of sight. distribution. We have modeled the thermal electron density according to the spiral arm models and the distribution of ionized hydrogen in the Galactic plane by Lockman (1976) and Cersosimo et. al. (1989) and have made predictions to compare with the surveys of Dwarakanath et al. (1990) at. 34.5 MHz and .Jones and Finlay (1974) at 29.9 MHz. The result confirms that the absorption model of the synchrotron emissivity in the Galactic plane is broadly corrected and illustrates the potential of the absorption technique.

• Journal of applied mathematics & informatics
• /
• v.13 no.1_2
• /
• pp.441-446
• /
• 2003

Let { $X_{n}$ , n $\geq$ 1} be a sequence of independent and identically distributed random variables with a common continuous distribution function F(x) and probability density function f(x). Let $Y_{n}$ = max{ $X_1$, $X_2$, …, $X_{n}$ } for n $\geq$ 1. We say $X_{j}$ is an upper record value of { $X_{n}$ , n$\geq$1} if $Y_{j}$ > $Y_{j-1}$, j > 1. The indices at which the upper record values occur are given by the record times {u(n)}, n$\geq$1, where u(n) = min{j｜j>u(n-1), $X_{j}$ > $X_{u}$ (n-1), n$\geq$2} and u(1) = 1. We call the random variable X $\in$ Beta (1, c) if the corresponding probability cumulative function F(x) of x is of the form F(x) = 1-(1-x)$^{c}$ , c>0, 0$\leq$x$\leq$1. In this paper, we will give a characterization of the beta distribution of the first kind by considering conditional expectations of record values.s.