여러가지 신뢰도에 근거한 자동차 보험료 예측

김영화,김미정,김명준,Kim, Yeong-Hwa,Kim, Mi-Jung,Kim, Myung-Joon 한국통계학회 2011 응용통계연구 Vol.24 No.2

Credibility theory is one of the most important theories of actuarial science to calculate the proper insurance premium. In this paper, the rule of relative exposure volume, the square root rule, the B$\"{u}$hlmann credibility and B$\"{u}$hlmann-Straub credibility with the basic concept of credibility have been introduced, Also, we estimate new premiums based on these methods for real data. As a result, the rule of relative exposure volume provides the highest accuracy. 합리적인 보험료를 책정하기 위해 사용되는 신뢰도 이론은 보험통계학의 중요한 주요 이론 가운데 하나이다. 본 논문에서는 신뢰도 이론의 기본 개념과 함께 유효대수 법칙, 제곱근 법 칙, B$\"{u}$hlmann 신뢰도, B$\"{u}$hlmann 신뢰도, B$\"{u}$hlmann-Straub 신뢰도 등을 소개하였다. 또한 이러한 방법들에 근거하여 새로운 보험료를 실제 자료를 시용하여 예측하였다. 결론적으로, 유효대수 법칙이 가장 정확한 예측력을 보였다.

Relationship Between Academic Stress and College Life Adaptation for Dental Hygiene Students: Focus on Self-efficacy, Burnout, Social Support

( Ji-yeon Oh ),( Jong-hwa Jang ) 융합연구학회 2018 융합연구학회지 Vol.2 No.1

The purpose of this study is to investigate the academic stress, self efficacy, burn out, social support and college life adaptation of dental hygiene students and their correlations with related factors influencing college life adaptation. A total of 265 students were selected as stratified sampling methods at the universities in which the department of dental hygiene was established nationwide. From September 1, 2015 to October 22, 2015, the self report questionnaire was used. The main variables were college life adaptation, academic stress, self efficacy, burn out, social support, and analyzed using SPSS 21.0. College life adaptation was 5.17 out of 9 points, academic stress was 2.88 points out of 6 points, self efficacy, burn out, and social support were 3.35, 2.60, and 3.54 out of 5, each respectively. Self efficacy and stress due to task and class were significant influences on individual-emotional adaptation in college life adaptation. In the case of college environment adaptation, exhaustion, self efficacy and social support were significant influencing factors. In the case of social adaptation, self efficacy and social support were significant influencing factors. Overall, academic stress and college life adaptation were closely related, and social psychological factors such as burn out, self efficacy and social support were mediated. Therefore, it is suggested that it should be applied to college education in order to increase adaptation of dental hygiene students, to reduce academic stress and burn out, and to develop intervention strategies that can enhance self efficacy and social support.

형태별 구리 및 아연 급여가 비육돈의 생산성, 영양소 소화율, 도체 및 육질 특성에 미치는 영향

김영화,유종상,박준철,정현정,조진호,진영걸,김해진,김인철,이상진,김인호,Kim, Y.H.,Yoo, J.S.,Park, J.C.,Jung, H.J.,Cho, J.H.,Chen, Y.J.,Kim, H.J.,Kim, I.C.,Lee, S.J.,Kim, I.H. 한국축산식품학회 2008 한국축산식품학회지 Vol.28 No.1

This study investigated the effects of copper and zinc sources on growth performance, nutrient digestibility, carcass traits and meat characteristics in finishing pigs. Dietary treatments included 1) inorganic copper ($CuSO_4{\cdot}5H_2O$ 30ppm), 2) organic copper (Cu-methionine, 30 ppm), 3) inorganic zinc (ZnO, 80 ppm) and 4) organic zinc (Zn-methionine, 80 ppm). ZnO treatment improved the ADFI (average daily feed intake) compared to Cu-met and Zn-met treatments (p<0.05) during 5 weeks of treatment. However, during the entire experimental period, the ADG (average daily gain), ADFI and F:G ratio (feed conversion ratio) were not significantly different among the treatments (p>0.05). DM and N digestibility were not significantly different among the treatments after 5 weeks (p>0.05). At the end of the experiment, DM and N digestibility were decreased with Zn-met treatment relative to the other three treatments. The pH value of meat from $CuSO_4$ treated pigs was greater than Zn-met and ZnO treated pigs (p<0.05). Sensory evaluation was carried out for randomly selected (n = 16) paired loin samples. Meat color levels were increased (p<0.05) with Cu treatments compared to Zn treatments. $CuSO_4$ decreased the marbling of meat relative to the other treatments (p<0.05). The firmness was greater with ZnO treatment compared to Cu-met and ZnO treatments (p<0.05). These results indicate that inorganic Zn can improve growth performance, however, inorganic Cu and Zn are as effective as organic Cu and Zn at improving nutrient digestibility, carcass traits and meat quality. This form of organic additive can be friendlier to the environment than inorganic supplements.

대만의 양돈현황 및 생산비 분석

김영화,Kim, Yeong-Hwa 대한양돈협회 1994 養豚 Vol.16 No.3

지상파 DTV 데이터방송의 시험 인증 서비스 현황 및 전망

김영화,양진영,최미애,Kim, Yeong-Hwa,Yang, Jin-Yeong,Choe, Mi-Ae 한국정보통신기술협회 2006 TTA저널 Vol.104 No.-

'환경보전, 삶의 질 향상' 환경기술개발로 뒷받침

김영화,Kim, Yeong-Hwa 환경보전협회 2006 환경정보 Vol.28 No.363

A Study on the Structure of the Yangsan Fault In the southern part of Kyeongju

김영화,이기화,Kim, Yeonghwa,Lee, Kiehwa The Korean Society of Economic and Environmental G 1987 자원환경지질 Vol.20 No.4

양산단층의 구조를 밝히는 연구의 일환으로 경주 남쪽지역을 대상으로하여 지질 및 저주파 전자탐사방법에 의한 단층탐사를 실시하였다. 그 결과 양산단층지역의 구조적 특성에서부터 파쇄대의 규모, 단층선의 위치 등에 대한 새로운 사실들이 밝혀졌으며, 단층파쇄대의 규모와 단층변의 위치에 있어서 지질 및 지전기학적 연구성과가 서로 일치됨이 확인 되었다. As a part of study on the structure of the Yangsan Fault, geological and VLF EM studies have been made in the fault area approximately between Kyeongju and Eonyang. The result provides comparatively clear information on the trace of the fault and extent of fracture zone as well as the structural characteristics of the Yangsan Fault area. The location of fault trace identified from this VLF EM study coincides well in general with that expected from geological information of the area. And the extent of fault fracture zone turn out to be characterized by U shaped low resistivity zone whose width increases from north to south.

조기이유방법과 조기이유시 주의할 점

김영화,Kim, Yeong-Hwa 대한양돈협회 1994 養豚 Vol.16 No.9

발달 독성학에서 비대칭 로짓 모형을 사용한 이진수 자료와 연속형 자료에 대한 결합분석

김영화,황범석,Kim, Yeong-hwa,Hwang, Beom Seuk 한국통계학회 2020 응용통계연구 Vol.33 No.2

하나의 개체에서 여러가지 측정치가 동시에 관찰되는 경우는 다양한 연구 분야에서 흔히 나타난다. 발달 독성학 연구에서는 특정 독성 물질의 각기 다른 수준에 노출된 임신한 어미 쥐에 대해 기형인 태아의 존재와 태아의 무게가 동시에 측정된다. 이런 두 변수를 결합하여 모형화하는 것은 각기 독립적인 두 모형으로 분석하는 것보다 더 효율적인 결과를 낸다고 알려져 있다. 대부분의 결합 모형은 정규분포를 랜덤효과로 가정하여 분석한다. 그러나 발달 독성학 연구에서처럼 반응변수들의 분포가 독성 물질이 변함에 따라 불규칙하게 변하는 경우 정규분포의 가정으로는 그 특징을 잡아낼 수 없게 된다. 본 논문에서는 이진수 자료와 연속형 자료에 대해 비대칭 로짓 모형을 사용한 베이지안 결합모형을 제시한다. 본 모형은 비대칭 로짓 모형을 사용함으로써 반응변수의 분포의 형태가 독성 물질의 수준에 따라 대칭/비대칭의 형태를 자유롭게 띨 수 있는 장점을 가지고 있다. 모형의 적합성을 살펴보기 위해 발달 독성학 연구에서 독성 물질 DEHP에 적용하여 그 결과를 확인해본다. It is common to encounter correlated multiple outcomes measured on the same subject in various research fields. In developmental toxicity studies, presence of malformed pups and fetal weight are measured on the pregnant dams exposed to different levels of a toxic substance. Joint analysis of such two outcomes can result in more efficient inferences than separate models for each outcome. Most methods for joint modeling assume a normal distribution as random effects. However, in developmental toxicity studies, the response distributions may change irregularly in location and shape as the level of toxic substance changes, which may not be captured by a normal random effects model. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint model for binary and continuous outcomes. In our model, we incorporate a skewed logit model for the binary outcome to allow the response distributions to have flexibly in both symmetric and asymmetric shapes on the toxic levels. We apply our proposed method to data from a developmental toxicity study of diethylhexyl phthalate.

시계열 회귀모형에 근거한 자동차 보험료 추정

김영화,박원서,Kim, Yeong-Hwa,Park, Wonseo 한국통계학회 2013 응용통계연구 Vol.26 No.2

보험료 및 보험료 구성요소에 대한 예측모형은 합리적인 보험료 결정에 필수적이다. 본 연구에서는 가변수 회귀모형, 독립변수 추가모형, 자기회귀 오차모형, 계절형 ARIMA 모형, 개입모형 등 적정한 자동차 대물 손해보험료 추정에 사용되는 다양한 모형을 소개하였다. 또한 실제 자동차 대물 보험료 자료를 이용하여 각 모형을 이용하여 보험료, 심도, 빈도 등을 추정하였으며, 모형의 추정결과는 추정치와 실제 자료값의 차이에 근거한 RMSE(Root Mean Squared Errors) 값을 통해 비교하였다. 실제 자료 분석 결과, 자기회귀 오차모형이 가장 좋은 성능을 보여주는 것을 알 수 있었다. An estimation model for premiums and components is essential to determine reasonable insurance premiums. In this study, we introduce diverse models for the estimation of property damage premiums(premium, depth and frequency) that include a regression model using a dummy variable, additive independent variable model, autoregressive error model, seasonal ARIMA model and intervention model. In addition, the actual property damage premium data was used to estimate the premium, depth and frequency for each model. The estimation results of the models are comparatively examined by comparing the RMSE(Root Mean Squared Errors) of estimates and actual data. Based on real data analysis, we found that the autoregressive error model showed the best performance.