• Journal of Preventive Medicine and Public Health
• /
• 제38권2호
• /
• pp.132-140
• /
• 2005

Objectives: To propose a risk-adjustment model from insurance claims data, and analyze the changes in cesarean section rates of healthcare organizations after adjusting for risk distribution. Methods: The study sample included delivery claims data from January to September, 2003. A risk-adjustment model was built using the 1st quarter data, and the 2nd and 3rd quarter data were used for a validation test. Patients' risk factors were adjusted using a logistic regression analysis. The c-statistic and Hosmer-Lemeshow test were used to evaluate the performance of the risk-adjustment model. Crude, predicted and risk-adjusted rates were calculated, and compared to analyze the effects of the adjustment. Results: Nine risk factors (malpresentation, eclampsia, malignancy, multiple pregnancies, problems in the placenta, previous Cesarean section, older mothers, bleeding and diabetes) were included in the final risk-adjustment model, and were found to have statistically significant effects on the mode of delivery. The c-statistic (0.78) and Hosmer-Lemeshow test ($x^2$=0.60, p=0.439) indicated a good model performance. After applying the 2nd and 3rd quarter data to the model, there were no differences in the c-statistic and Hosmer-Lemeshow $x^2$. Also, risk factor adjustment led to changes in the ranking of hospital Cesarean section rates, especially in tertiary and general hospitals. Conclusion: This study showed a model performance, using medical record abstracted data, was comparable to the results of previous studies. Insurance claims data can be used for identifying areas where risk factors should be adjusted. The changes in the ranking of hospital Cesarean section rates implied that crude rates can mislead people and therefore, the risk should be adjusted before the rates are released to the public. The proposed risk-adjustment model can be applied for the fair comparisons of the rates between hospitals.

• 한국지역사회생활과학회지
• /
• 제15권3호
• /
• pp.167-177
• /
• 2004

This study is designed to understand purchase motivation for garment depending on demographic factors among college students in Yanbian, China. Questionnaire was used for measurement tools to study the subject of the thesis. The main study was conducted against 450 college students from May 17 to June 5, 2001. The data for the study were analyzed using SAS PC program for frequency distribution, percentage, t -test, and one way ANOVA. The purchase motivation for garment are affected by demographic factors such as gender, average monthly household income, monthly expense for clothing. The result was showed as follows: A meaningful difference showed in 3 areas 'to try a new trend, impulsive buying at the store display, discount advertising' depending on the gender in terms of purchase motivations, and in all the three areas, male students showed a higher ranking. But in other motivation areas, no difference was noticed in terms of gender. In terms of purchase motivation based on monthly income, only one area 'impulse buying from a store display' showed a meaningful difference. Respondents with an average monthly household income above 2,000 yuan showed a higher tendency of 'impulse buying' compared to those with below 500 yuan or those with between 500-2,000yuan. Those with the average monthly household income below 500 yuan showed the lowest ranking in the impulse buying. In other areas of purchase motivation, average monthly household income was not an important element. A meaningful difference showed in 4 areas, 'to try a new trend, impulse buying from a store display, discount advertising', and 'for a change of mood' in the product motivation based on expense on clothing. Respondents with an average monthly expense for clothing above 100 yuan showed a higher ranking in all 4 areas than those with less than 100 yuan. In other areas, the average monthly clothing expense didn't give any impact.

• 노동경제논집
• /
• 제40권2호
• /
• pp.1-29
• /
• 2017

본 연구는 동료(peer)에 대비한 학생의 상대적인 학업성취가 진로 결정에 어떠한 영향을 주는지를 살펴본다. 구체적으로 학교 내에서 학생들의 상대적인 수학 순위가 이과 선택에 미치는 영향을 분석하였다. 분석을 위해 서울시 소재 학생들의 패널데이터를 이용하였으며, 수학 성적을 통제하더라도 상대 순위가 낮은 경우 이과에 진학할 확률이 11%포인트 이상 감소함을 확인하였다. 높은 상대 순위는 여학생에게 추가적인 양의 이과 진학 효과를 나타내 상대 순위가 성별로 다르게 작용함을 보였다. 분석 결과에 따르면 상대 순위효과 중 약 12%만이 자신감과 같은 주관적 평가에 의해 설명되며, 이로 미루어보아 내신 성적을 통한 경로가 더 지배적일 것으로 추측할 수 있다.

• 한국인터넷방송통신학회논문지
• /
• 제19권1호
• /
• pp.1-8
• /
• 2019

대량의 로그 자료로부터 가장 적합한 정보를 추출하기 위한 방법 중 귀납 추리를 이용한 방법이 있다. 본 논문에서는 디지털 포렌식 분석에서 침입 흔적 로그의 순위를 결정하기 위하여 귀납 추리를 이용한 방법 중 분류에 있어서 우수한 SVM(Support Vector Machine)을 이용한다. 이를 위하여, 훈련 로그 집합의 로그 데이터를 침입 흔적 로그와 정상 로그로 분류한다. 분류된 각 집합으로부터 연관 단어를 추출하여 연관 단어 사전을 생성하고, 생성된 사전을 기반으로 각 로그를 벡터로 표현한다. 다음으로, 벡터로 표현된 로그를 SVM을 이용하여 학습하고, 학습된 로그 집합을 기반으로 테스트 로그 집합을 정상 로그와 침입 흔적 로그로 분류한다. 최종적으로, 포렌식 분석가에게 침입 흔적 로그를 추천하기 위하여 침입 흔적 로그의 추천 순위를 결정한다.

• Journal of the Korean Statistical Society
• /
• 제17권2호
• /
• pp.61-80
• /
• 1988

For testing homogeneity of scale parameters aginst ordered alternatives, some nonparametric test statistics based on pairwise ranking method are proposed. The proposed tests are distribution-free. The asymptotic distributions of the proposed statistcs are also investigated. It is shown that the Pitman efficiencies of the proposed rank tests are the same as those of the corresponding two-sample rank tests in the scale problem. A small-sample Monte Carlo study is also performed. The results show that the proposed tests are robust and efficient.

• 품질경영학회지
• /
• 제19권1호
• /
• pp.16-27
• /
• 1991

Propose three rank tests based on different kinds of ranking methods for comparing several treatments with a control in a randomized block experiment. Monte Carlo power simulation study is examined in some small sample sizes and configurations to recommend a better test for applications.

• 품질경영학회지
• /
• 제40권4호
• /
• pp.497-512
• /
• 2012

Purpose: Most major countries have their own set of qualifications called national quality awards to measure the quality of companies and organizations. This study analyzes 3 different national quality awards and compare with the result from Korean quality awards conducted by Ministry of knowledge and Economy and Korea institute for advancement of technology. Methods: We tested 17 technoparks out of 18 technoparks in Korea and see how different the results can be depends on the value weights. We closely looked at each qualifications and tables of different countries' awards and compared with one used in Korea. Finally we proposed some suggestions to use not only domestic model but also international ones to be objective and add efficiency to organizations. Results: Depend on similarity of qualifications and weights, there were countries with different results and these caused score and ranking changes. Nevertheless, there was a comparison that did not make any changes on both score and ranking. Conclusion: We recognized the limitation that a standardized quality variation cannot be enough sources to test and analyze technoparks with different size and criteria. Integrating global standards and flow would be the first step to help grow technoparks and organizations placed in Korea in days to come.

• 한국인쇄학회지
• /
• 제29권2호
• /
• pp.15-32
• /
• 2011

In printing, managing color means that how closely its color reproducts and printing supplier meets customers' requirements. When applying device profiles, it depends on properties of the devices. But color management of domestic digital prints is accomplished more scientifically and objectively than any other printing. According to this paper addresses a method of evaluating between proof prints and offset prints which are produced by identical date on the field. We evaluate two cases normal proof prints and domestic offset prints based on standardized color data analysis and subjective data analysis. We gathered objective data by measuring solid density, $CIEL^*a^*b^*$ and ${\Delta}E^{*_}{ab}$. Furthermore, we evaluated the offset prints and proof prints through human eyes to decide the ranking.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권2호
• /
• pp.144-147
• /
• 2015

Question Answering (QA) 서비스는 사용자의 자연어 질의에 대응하는 정확한 답변을 제공하는 시스템이다. 본 연구는 특정 도메인에 관련한 사용자들의 질문에 대해 QA 서비스가 자동으로 대응하는 방법에 관한 연구이다. 이를 수행하기 위하여 사용자의 자연어 질문을 이해하고, 정형 데이터 및 비정형 데이터로부터 사용자 질문에 적합한 답변을 도출하여 제공하는 방법을 제시한다. 실험 결과 top 1 accuracy 68%, top 5 accuracy 77% 결과를 얻었다. 또한 본 논문은 QA 시스템 내부 모듈이 전체 accuracy에 미치는 영향에 대해서도 기술하였다.

• ETRI Journal
• /
• 제45권3호
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.