• 아태비즈니스연구
• /
• 제11권4호
• /
• pp.37-48
• /
• 2020

Purpose - This study empirically investigates whether the risk property included in fat-tails of return distributions is systematic or unsystematic based on the devised statistical methods. Design/methodology/approach - This study devised empirical designs based on two traditional methods: principal component analysis (PCA) and the testing method of portfolio diversification effect. The fatness of the tails in return distributions is quantitatively measured by statistical probability. Findings - According to the results, the risk property in the fat-tails of return distributions has the economic meanings of eigenvalues having a value greater than 1 through PCA, and also systematic risk that cannot be removed through portfolio diversification. In other words, the fat-tails of return distributions have the properties of the common factors, which may explain the changes of stock returns. Meanwhile, the fatness of the tails in the portfolio return distributions shows the asymmetric relationship of common factors on the tails of return distributions. The negative tail in the portfolio return distribution has a much closer relation with the property of common factors, compared to the positive tail. Research implications or Originality - This empirical evidence may complement the existing studies related to tail risk which is utilized in pricing models as a common factor.

• Journal of the Korean Data and Information Science Society
• /
• 제23권2호
• /
• pp.235-245
• /
• 2012

로지스틱판별분석은 금융 분야에서 유용하게 사용되고 있는 통계적 기법으로 신용평가 시 해석이 쉽고 우수한 분별력으로 많이 활용되고 있지만 종속변수에 대한 설명변수들의 비선형적인 관계를 설명하는 부분에는 한계점이 있다. 일반화가법모형은 로지스틱판별모형의 장점과 함께 종속변수와 설명변수 사이의 비선형적인 관계도 설명할 수 있다. 그러나 연속형 설명변수의 수가 대단히 많은 경우이 두 방법은 모형에 유의한 변수를 선택해야하는 문제점이 있다. 따라서 본 연구에서는 다수의 연속형 설명변수들을 공통요인분석자혼합모형에 의한 차원축소를 통해 변환된 소수의 요인점수들을 일반화가법모형의 새로운 연속형 설명변수로 사용하여 신용분류를 하는 방법을 제시한다. 실제 금융자료를 이용하여 로지스틱판별모형과 일반화가법모형, 그리고 본 연구에서 제안한 방법에 의한 정분류율을 비교한 결과 본 연구에서 제안한 방법의 분류 성능이 더 우수하였다.

• 응용통계연구
• /
• 제37권2호
• /
• pp.255-263
• /
• 2024

GDP는 한 나라의 가계, 기업, 정부 등 모든 경제 주체가 일정 기간 동안 창출한 재화와 서비스의 시장 가치의 합을 나타낸다. GDP를 통하여 국가의 경제 규모를 파악할 수 있으며, 정부의 정책 방향에 영향을 미치는 대표적인 경제 지표이므로 이에 대한 연구가 다양하게 이루어지고 있다. 본 논문에서는 G20 국가들의 주요 거시경제 지표를 활용하여 dynamic factor model 기반의 GDP 성장률 예측 모델을 제시하였다. 추출된 factor를 다양한 회귀분석 방법론과 결합하여 그 결과들을 비교하였으며, 기존의 전통적인 시계열 예측방법인 ARIMA 모델, common component를 이용한 예측 등도 함께 비교하였다. COVID 이후 지표의 변동성이 큰 점을 고려하여 예측 시기를 COVID 전후로 나누었으며, 그 결과 factor에 대해 ridge regression과 lasso regression을 적용하여 예측한 경우 가장 좋은 성능을 나타내었다.

• Clinical and Experimental Pediatrics
• /
• 제49권8호
• /
• pp.821-829
• /
• 2006

Hemophilia is the most common coagulation disorder. It has a long history. Hemophilia A is caused by FVIII gene mutation, and hemophilia B by FIX gene mutation. Those genes are located on X chromosome long arm. Bleedings in hemophiliacs predominantly occur in joints and muscles. Because those site are insufficient in tissue factor to induce hemostasis. Among joints knee, ankle and elbow are most frequently affected because their synovial structure is vulnerable to injury compared to other joints. Hemophilia is diagnosed with factor assay. Severe hemophilia is below 1% of FVIII : C, moderate between 1% and 5%, mild over 5%. Carrier detection and prenatal diagnosis have been conducted with RFLP-based linkage analysis and DNA sequencing. Mainstay of treatment is factor replacement therapy so far. Bleedings can be controlled by infusion of factor concentrates. Hemophilc arthropathy and muscle contracture are representative sequelae. Complications of facotor replacement therapy are inhibitor development and infections. Hemophiliacs with inhibitor should be managed with large dose factor concentrate, bypassing agent, ITI and immunosuppression. Ultimately, hemophilia could be cured by gene therapy.

• Asian-Australasian Journal of Animal Sciences
• /
• 제21권3호
• /
• pp.309-313
• /
• 2008

The insulin-like growth factor binding protein 3 (IGFBP3) has been investigated as a candidate gene for growth promoting effects in beef cattle and a modulator of IGF bioactivity. Previously, we have reported twenty two sequence variants discovered in Korean native cattle (Hanwoo). In this study, we examined the association between gene-specific polymorphisms of IGFBP3 and cold carcass weight (CW) and marbling score (MS) among Korean native cattle. Among twenty two polymorphisms, four common polymorphic sites (-854G>C, -100G>A, +421G>T and +3863C>A) were genotyped in our beef cattle (n = 437). Statistical analysis revealed that one common polymorphism in the promoter region (-854G>C) showed putative associations with MS (p = 0.03). IGFBP3 variation/haplotype information analyzed in this study will provide valuable information into strategies for the production of a commercial line of beef cattle.

• 한국의류산업학회지
• /
• 제6권1호
• /
• pp.102-108
• /
• 2004

The anthropometric measurement and the photometric measurement for have been conducted 358 children from 4 years old to 6 years old to design children's clothing. The characteristics of body type were grasped among total 44 measurement items according to the aging, being extracted seven factors from factor analysis. From cluster analysis among the seven factors the three body types were classified. Type 1 shows low fat body with a small figure and short upper body. The body has a round belly and waist. Type 2 shows the fattest body with an average height. The body has been backed with lower shoulders. Type 3 shows common fat body with a high height and a big figure. The body shows crooked round back with a big upper body and rising shoulders.

• 한국항해항만학회지
• /
• 제39권6호
• /
• pp.553-559
• /
• 2015

2014년 우리나라 선용품 시장의 규모는 5조 7천400억 원 정도로 추정되며, 대부분이 부산, 울산 등 경남권에서 이뤄지지만, 관련업체가 400여 개나 난립해 대부분 평균 매출이 20억 원 미만으로 영세한 수준이다. 또한, 세계 해운항만산업의 불황과 중국을 비롯한 개발도상국들의 저가 선용품의 생산 및 공급으로 인해 국내 선용품 업계의 전망은 그다지 밝지 않는 상황이다. 이에 본 논문에서는 선용품 산업의 활성화를 위한 방안 중 하나로 선용품 공동물류를 선택하였고, 공동물류를 운영함에 어떠한 요인이 중요한지에 대한 연구를 진행하였다. 선행연구 고찰을 통해 공동물류 운영과 관련된 16가지 요인을 도출하여 AHP, IPA 기법을 활용해 분석 하였다. 분석결과 비용측면이 선용품 공동물류를 운영하는 데 있어 가장 중요한 요인으로 나타났다.

• 대한토목학회논문집
• /
• 제34권6호
• /
• pp.1837-1844
• /
• 2014

철도외의 다른 산업분야에서 안전문화 측정에 대한 연구가 활발히 진행된 것과 달리, 국내 철도분야의 안전문화 성숙에 대한 연구는 아주 초보적인 단계에 머물러 있다. 본 연구는 철도안전문화 평가의 신뢰성을 높이기 위해 설문문항 구성 시 어떻게 평가요인을 구성하고, 설문문항 그룹이 해당 요인을 얼마나 잘 대변하고 있는지, 그리고 그룹을 정의한 기준이 다른 공통 속성을 갖는지 여부를 분석하기 위해 내적 신뢰도 및 요인 분석을 실시하였다. 요인분석 결과 기존 5개에서 7개 요소로 도출되었고, 그에 따른 설문문항의 그룹화 및 요소의 이름이 재부여 되었다. 이는 문항간에 내제된 공통 속성을 잘 파악하는 것이 설문자와 피 설문자 간의 견해 차이를 줄이는 데 중요함을 의미한다. 또한 새로운 요인 분류에 대한 문항들의 내부 신뢰도 확인결과 여전히 이전과 비교하였을 때 높게 관측되어 그 분류가 적절함을 확인하였다. 본 연구는 철도안전문화 평가의 신뢰성을 높이는데 통계적인 방법을 활용하여 기존 설문조사 결과를 검증하고 어떻게 접근해야 하는지 다루고 있어 관련분야에서 많이 활용될 것으로 기대된다.

• 한국환경보건학회지
• /
• 제48권4호
• /
• pp.236-243
• /
• 2022

Background: In the case of multiple exposures to different types of heavy metals, such as the conditions faced by residents living near a smelter, it would be preferable to group hazardous substances with similar characteristics rather than individually related substances and evaluate the effects of each group on the human body. Objectives: The purpose of this study is to evaluate the utility of factor analysis in the assessment of health effects caused by exposure to two or more hazardous substances with similar characteristics, such as in the case of residents living near a smelter. Methods: Heavy metal concentration data for 572 people living in the vicinity of the Janghang smelter area were grouped based on several subfactors according to their characteristics using factor analysis. Using these factor scores as an independent variable, multiple regression analysis was performed on health effect markers. Results: Through factor analysis, three subfactors were extracted. Factor 1 contained copper and zinc in serum and revealed a common characteristic of the enzyme co-factor in the human body. Factor 2 involved urinary cadmium and arsenic, which are harmful metals related to kidney damage. Factor 3 encompassed blood mercury and lead, which are classified as related to cardiovascular disease. As a result of multiple linear regression analysis, it was found that using the factor index derived through factor analysis as an independent variable is more advantageous in assessing the relevance to health effects than when analyzing the two heavy metals by including them in a single regression model. Conclusions: The results of this study suggest that regression analysis linked with factor analysis is a good alternative in that it can simultaneously identify the effects of heavy metals with similar properties while overcoming multicollinearity that may occur in environmental epidemiologic studies on exposure to various types of heavy metals.

• 한국환경과학회지
• /
• 제17권3호
• /
• pp.315-323
• /
• 2008

Based on the result of extraction of common factors executed in order to elucidate the visual attributes of street scenery by types through the rotation of 23 adjective variables by Varimax, the visual attributes expressed after the construction of the facilities using street scenery were anylized to be 4 factors including factor 1 through factor 4. Theexplanation of the 4 factor groups to explain the entire distribution was 65.3% and these factor groups are the psychological attributes felt when using facilities are constructed by securing the street spaces in downtowns and the factors were named as naturalness(factor 1), locality(factor 2), identity(factor 3) and clarity(factor 4) respectively. Based on the result of one-way layout distribution analysis, the preferences for street scenery by types were found out to show considerable differences at 1 % significance level. Based on the result of multiple regression analysis, all of the factors explaining preferences including factor 1 through factor 4 were significant at 1 % significance level. In case other conditions are constant, if the values of the adjective variables related to locality(factor 2) increase by 1 unit, the preferences which are the values of dependent variables will increase by 0.709. The variable with the largest relative contribution among the 4 factor groups was the locality(factor 2) factor group and on the contrary, it was found that the independent variable with least influences was the clarity(factor 4) factor group.