위벽에 종양으로 발현한 췌장 가성 낭종 1 예

오광식,최재홍,채희복,윤세진,박선미,성노현,배일헌,최기원,권순길,신향미 대한소화기내시경학회 2001 Clinical Endoscopy Vol.23 No.4

We report a case of pancreatic pseudocyst presenting as an intramural gastric tumor on upper gastrointestinal examination, endoscopic ultrasound and computed tomography of the abdomen. Pancreatic pseudocysts in the stomach wall is rare and the most of them presented as a cystic mass, but this case was presented as a gastric mural solid tumor. Exploration revealed an about 4×4×2 ㎝ sized round mass at the midbody of great curvature of stomach, it was in the muscle layer, and removed by surgical operation. The correct diagnosis of this case was established postoperately on the pathologic examination revealed pancreatic pseudocyst.

Eight Stenus Latreille species (Coleoptera, Staphylinidae, Steninae) in Korea

오광식,조영복,Oh, Kwang-Sik,Cho, Young-Bok Korean Society of Applied Entomology 2015 한국응용곤충학회지 Vol.54 No.4

한국산 딱부리반날개속(Stenus Latreille)의 8종에 대해 보고한다. 이들 중, 3종(Stenus burjaetus Puthz, S. depressus Puthz and S. gibbicollis J. Sahlberg)은 한반도산 미기록종이고, 나머지 5종은(S. coronatus coronatus L. Benick, S. decoratus L. Benick, S. koreanus Puthz, S. rugipennis Sharp and S. sharpi Bernhauer and Schubert)은 남한에서 처음 보고되는 종들이다. 8종의 성충 사진, 수컷의 생식기 및 9번째 복판에 대한 그림과 한국산 딱부리반날개속의 종 검색표를 제공한다. Eight species of the genus Stenus Latreille are documented for the first time in Korea. Among them, three species, Stenus burjaetus Puthz, S. depressus Puthz and S. gibbicollis J. Sahlberg, are recorded for the first time in the Korean peninsula. And five species, S. coronatus coronatus L. Benick, S. decoratus L. Benick, S. koreanus Puthz, S. rugipennis Sharp and S. sharpi Bernhauer and Schubert, are newly recorded in South Korea. The adult photographs, illustrations of aedeagus and male sternite IX of them, and a taxonomic key of Korean Stenus species are presented.

On the Linearity Test based on CERES

오광식,김대학 한국자료분석학회 2006 Journal of the Korean Data Analysis Society Vol.8 No.5

Conditional Expectations and RESiduals(CERES) plots may be useful for obtaining an impression of curvature as a function of selected covariates x2 in regression problems in which the covariate vector x is partitioned as x^{ T } ``=``(x_{ 1 } ^{ T } ,x_{ 2 } ^{ T } ) In this paper, we consider the problem of checking the linearity of selected covariates x2 hrough the idea of smoothing of a CERES plot. A modified pseudo-likelihood ratio test statistic is derived as a ratio of quadratic forms. The distribution of this statistic is calculated numerically by using Johnson curves. Monte Carlo simulation is conducted to show the power of the test for small sample sizes.

확률 및 통계와 교원임용시험

오광식 한국데이터정보과학회 2017 한국데이터정보과학회지 Vol.28 No.6

In this paper, we analyze and discuss the trend of the probability and statistics problems that have been made in the public secondary school teacher employment exam for mathematics teachers. In order to properly teach the national mathematics curriculum in 2015 in terms of content and function, we investigate the probability and statistics contents that a mathematics teachers should know. We also analyze the contents and trends of the items that have been submitted for 15 years in public secondary school teacher employment exam, and discuss the contents, scope, level and direction of the future contents. In conclusion, considering the significance of the Big Data in the 4th industrial revolution, the problems of statistical thinking of data and probability, exploratory data analysis, sample survey, and statistical inference are needed more. 본 연구는 확률과 통계의 내용을 올바르게 지도할 수 있는 역량을 갖춘 수학 교사를 선발하기 위한 중등학교 수학교과 임용고사는제 중에서 확률과 통계 영역의 출제 경향을 분석하고, 앞으로의 출제 방향과 수준에 대하여 논의하고자 한다. 동시에 학교 수학 교사들에게 확률과 통계 단원을 지도하기 위해서 갖추어야 할 내용에 대한 일반적인 가이드를 제시하고자 한다. 첫째, 2015년 개정 고시된 교육과정의 수학 교과 중에서 확률과 통계 단원의 편제와 내용체계, 주요 변화 내용을 조사한다. 둘째, 중등교원임용시험에 15년간 출제 된 확률과 통계 단원의 문제들을 분석한다. 셋째, 기존의 출제 문제들이 중등학교의 확률과 통계를 올바르게 교육할 수 있는 자질을 갖춘 교사를 선발할 수 있는지에 대하여 검토한다. 마지막으로, 앞으로의 출제 내용, 범위, 수준, 그리고 방향에 대해서 논의한다. 결론적으로 4차 산업혁명시대를 맞이하여 빅 데이터의 중요성을 감안한다면 자료와 확률에 대한 통계적사고, 탐색적자료분석, 표본조사, 통계적 추론 그리고 공학적 도구의 활등 등의 출제가 더욱 필요하다고 본다.

조건부 기대치와 잔차의 점도표를 이용한 선형모형의 곡률조사

오광식 대구효성가톨릭대학교 1995 연구논문집 Vol.50 No.1

In regression diagnostics, it is necessary to detect curvature of g(.) as a function of selected covariates in the semiparametric model. Partial residual plots(PRES) have been used when covariats are independent. Howerever, the usefulness of these plots for obtaining a good impression of curvature can depend on the behavior of the covariates through the conditional expectation. Cook(1993) suggested conditional expectation and residual plots(CERES). In this paper we investigate the properties of residual plots including PRES, augmented PRES, and CERES plots. Partial residual plots (PRES0 seem to perform best under linear conditional expectation or independet covatiats. Augmented partial residual plots (APRES) allow conditional expectation to be a quadratic function. Conditional expectation and residual plot (CERES) may be useful for obtaining an impression of curvature as a function of selected covariates when the conditional expectation is neither linear nor quadratic. Illustrations and Splus program are given in section 4.

선형회귀모형에서 다중특이치 검출에 관한 연구

오광식,박외정 대구효성가톨릭대학교 자연과학연구소 1994 基礎科學硏究論集 Vol.1994 No.1

In regression diagnostics, a number of outlier measures based on various statisti-cal tools have been discussed. These measures usually pay attantion to detecting individual outlier. However, there exists a situation in which observations are mul-tiple but not individual outliers or the other way about. The situation is refered to as a masking effect which means that the outlier of one observation is masked by the presence of another observation. The multiple outlier is often overlooked be-cause it is much more difficult to detect than the individual outliers. We propose a new expression of John and Draper's outlier sum of square. The advantages from the theroretical point of view are that the expression is based not only on the mutiple case but also on the single case, and that we can detect multiple outliers with the masking effect by investigating the difference between the multiple outliers and sum of the individual outliers. Furthermore we suggest a search method for multiple outliers after investigating some properties of the new expression.

Data Mining based on Regression Diagnostics

오광식 한국자료분석학회 2004 Journal of the Korean Data Analysis Society Vol.6 No.6

Among the data mining techniques, model building for regression should be based on the regression diagnostics such as selection of influent variables or observations. But the existing regression method is not practical for the huge data set. In this paper, a new regression diagnostic method for detecting influential observations which is useful for huge data sets is proposed. The proposed method is compared to the existing diagnostic method through simulations.

비행간섭트랩에 포획된 속리산국립공원내의 송장벌레류 종구성 및 풍부도의 계절적 변동

오광식,김도성,조영복,Oh, Kwang-Sik,Kim, Do-Sung,Cho, Young-Bok 한국응용곤충학회 2011 한국응용곤충학회지 Vol.50 No.3

Changes in insect communities are one of the best indicators of environmental changes. A survey was conducted using the Flight Interception Trap (FIT) method to check the changes of species composition and abundance of silphids at Mt. Sokrisan National Park from April to October in 2003 to 2007. A total of 9,704 individuals of six silphid species were examined by FIT. Among them, Nicrophorus quadripunctatus was the most dominant species with 8,763 (90.3%) individuals. There were only 971 (9.7%) individuals of the other five species. The seasonal abundance of silphids peaked in July and August. The annual abundance has decreased gradually since 2004. Therefore, the changing patterns of species composition and abundance of silphids checked by long-term monitoring could be used as environmental indicators which indirectly show the environmental changes of Mt. Sokrisan National Park. 곤충 군집의 변화는 서식지 환경의 변화를 파악할 수 있는 척도가 된다. 속리산국립공원에서 2003년부터 2007년까지 월별(4월-10월)로 Flight Interception Trap (FIT)을 이용하여 송장벌레류의 종 구성과 풍부도의 변화를 알아보기 위한 조사를 실시하였다. 그 결과, 6종 9,704개체가 조사되었는데, 이 중 넉점박이송장벌레(Nicrophorus quadripunctatus)가 8,763개체(90.3%)로 가장 높은 우점도를 보였다. 넉점박이송장벌레를 제외한 나머지 5종은 971개체(9.7%)에 불과하였다. 송장벌레 6종의 계절적 풍부도 변화에 따르면 7월과 8월이 최성기인 것으로 나타났다. 또한 연간 풍부도는 2004년 이후 점차 감소하는 경향을 보이고 있다. 장기간의 모니터링 결과, 환경지표종으로 활용이 가능한 송장벌레류의 종구성과 풍부도 변화는 속리산의 기후변화를 간접적으로 나타내고 있음을 시사한다.

EM 알고리즘을 통한 회귀계수 추정

오광식,김칠화 대구효성가톨릭대학교 자연과학연구소 1989 基礎科學硏究論集 Vol.3 No.-

In regerssion analysis, the incomplete data in which some variables are unrecorded for some cases, may be occured. Since the standard methods of analysis can be applied directly only to complete data sets, additional techniques are needed. In this paper, EM algorithm(expectation & maximization) which is a technique for esti-mating parameters of incomplete multivariate data, MLE, and MSE for the multiple regres-sion via EM algorithm are presented. In practical example and a simulation, the LS estimates using the complete data, the LS estimates using the complete data which is discarded the case containing missing values,the LS estimates using maximally available pairs in the sample variance, the LS estimatesusing fill-in methods are included for comparisons with the incomplete-data estimates by EM algorithm. Results are shown in Table 1-9. In the sense that the m.1.e's of ?, ∑, β and MSE by EM algorithm are uniformly closer to the complete-data results(the results which we would have obtained if the data were complete.) than those of the usual methods, as shown in Table 1-9, the gain in utilization of the incomplete cases by the EM procedure is quite obvious in these examples. Thus, we have obtained the fact that the EM procedure is more efficient than those of the usual methods.

제 20 차 대한신장학회 춘계학술대회 : 신 청소율 검사 (renal clearance test) 를 이용하여 진단한 Gitelman 증후군 2예

오광식,박영선,김형삼,김혜영,엄재호 대한신장학회 2000 춘계학술대회 초록집 Vol.2000 No.-

N/A