효율성과 목표원가를 반영한 병원예산 원가차이 분석 모형 설계

오동일(O Doug-Il) 한국산학기술학회 2013 한국산학기술학회논문지 Vol.14 No.2

본 연구는 DEA모형에 바탕을 둔 표준원가에 기초한 원가차이 분석의 개념을 구현할 수 있는 모형을 설 계하고 69개 종합병원의 투입‧산출물을 이용해 효율성 분석과 원가관리 방안을 살펴보았다. 이를 위해 DEA모형을 통해 달성가능한 목표원가를 구하고 이를 실제원가와 비교하여 차이분석모형의 틀을 구축하였다. 또한 이 모형을 바탕으로 의사‧간호사 인건비 정보를 구해 2008년도 결산기준 69개 종합병원의 표준원가차이를 구하고 이를 기술적 비효율성으로 인한 원가차이, 가격 비효율성에 기인한 원가차이, 표준예산원가 원가차이로 분리하여 원가관리의 새 로운 방식을 제시할 수 있었다. 또한 실증분석을 통해 69개 종합병원은 병상수와 같은 규모를 늘리는 것이 효율성 개선에 기여하지 않으며 오히려 예산목표원가 관리 측면에서는 비효율적인 것으로 나타나 규모 확장 일변도의 전 략을 수정할 필요가 있는 것으로 나타났다. This study aims to develop DEA model which can look into budget cost variance analysis tool based on standard cost using 68 hospital’s input and output data. For accomplishing this purpose, by introducing new DEA model which can get an attainable target cost, we can decompose an actual cost difference into several meaningful sub variances. Also based on the 2008 general hospital data, this model can make variance analysis between actual cost and target cost. Total variance can be divided into technical inefficiency variance, price inefficiency variance, allocation inefficiency variance. This study introduces that by using target budget cost concept, traditional actual cost variance can be divided into a technical variance, price variance, budget variance. Finally, we can get result which confirms there does not exist favorable size effects on efficiency and cost management in running a general hospital.

Risk Analysis and Supply Chain Coordination for Optimal Operation in E-Commerce Environment with Uncertainties in Demand and Customer Returns

Yuta Saito,Etsuko Kusukawa 대한산업공학회 2018 Industrial Engineeering & Management Systems Vol.17 No.3

This paper discusses risk analysis and supply chain coordination (SCC) for the optimal operation in a supply chain under e-commerce environment (e-SC) with the uncertainties in product demand and customer returns. An e-SC consists of a retailer and a manufacturer. The return handlings are discussed regarding customer returns and unsold products. A retailer receives customer returns from a market once and resells the resalable returns in the same market. A manufacturer buys back the unsold products and the un-resold customer returns from the retailer, considering the difference of quality between them. The mean-variance analysis (MVA) with three risk attitudes regarding the above uncertainties is discussed: risk-neutral attitude maximizing the decision maker’s expected profit in e-SC, risk-averse attitude with negative consideration of variance of the relevant profit, and risk-prone attitude with positive consideration of the variance. Using MVA, the optimal operations for product order quantity, the unit retail price and refund ratio of customer returns under the decentralized e-SC (DSC) and the integrated e-SC (ISC) are determined. The analysis numerically verified that each risk attitude on product demand and customer returns affected the optimal operations under DSC and ISC. SCC adjusting the unit wholesale price and buyback prices between members under ISC can shift to ISC.

반복측정 분산분석(Repeated measure ANOVA)의 적용논문 분석

민효숙 충남대학교 간호과학연구소 2005 충남대 간호학술지 Vol.8 No.1

The purpose of this study was to analyze nursing research using Repeated measures analysis of variance. When the measurements can be thought of as responses to levels of an experimental factor of interest, the correlation can be taken into account by performing a repeated measures analysis of variance. In repeated measures analysis of variance, the effects of interest are (1) between - subject effects (such as GROUP in the previous example) (2) within - subject effects (such as TIME in the previous example) (3) interactions between the two types of effects (such as GROUP * TIME in the previous example) The ultimate goal for nursing discipline is to promote health of the human. Understanding and doing the Repeated measures analysis of variance in correct way is considered to be our goal outcome to develop more scientific empirical knowledge.

벡터자기회귀모형을 통한 교통량 예측 -신갈 지역 중심으로-

김아현,박노진 한국자료분석학회 2014 Journal of the Korean Data Analysis Society Vol.16 No.1

With the continuous increasing in the volume of the traffic, the exact forecasting is emerging as one of the principal challenges these days. Even though neural network, regression analysis and time series analysis have already been studied as traffic forecasting model, in this study, we am going to find out the model using vector auto-regressive. Vector auto-regressive is the way of combination regression analysis with time series analysis. It expands the traditional ARMA to multivariate model. In this study, we have referred to the traffic data of Singal-Suwon, Singal-Masung, Singal-Dongsuwon, Singal-Seoul, Suwon-Kiheung sections from January 2004 to December 2012 from the materials of Korea Expressway Corporation. For the exact analysis, we did log transform after eliminating seasonal factors of materials. We set up the forecasting model through VAR, compared the performances with univariate time series. In addition, we examined the influence of variable in the VAR with using impulse response analysis and the relative importance of individual explanatory variables using variance decomposition analysis as well. As the result of the analysis, VAR has a better predictive power than univariate time series to a certain degree. It also shows the relative importance of individual explanatory variables. 교통량이 지속적으로 증가함에 따라 교통량을 정확히 예측하는 것이 중요한 과제로 떠오르고 있다. 기존 교통량 예측 모형으로 신경망, 회귀분석, 시계열 등이 많이 연구되었다. 본 논문에서는 벡터자기회귀(vector auto-regressive; VAR)를 적용하여 교통량 예측 모형을 개발하였다. 한국도로공사에서 제공하는 2004년 1월부터 2012년 12월까지의 신갈-수원, 신갈-마성, 신갈-동수원, 신갈-서울, 수원-기흥 구간의 교통량 자료를 사례로 이용하였다. 특히, 신갈-마성 구간을 중심으로 다른 구간들과의 관계를 찾고자 하였다. VAR을 통해 예측모형을 설정하고, 단변량 시계열모형과 예측 성능을 비교하였다. 충격반응함수를 통해 신갈-마성 구간에 대한 VAR모형 내 다른 구간들의 영향을 살펴보고, 분산분해를 통해 개별 구간들의 신갈-마성 구간 예측에 대한 상대적 중요성을 알아보았다. 관심의 대상인 신갈-마성 구간의 교통량에 대한 주변 구간들과의 수리적 모형을 구축하였고 주변 구간들의 영향력을 수치적으로 시각적으로 확인하였다. 신갈-마성 구간에 대한 인접 구간들의 영향력을 파악함으로써 차후 도로 건설 및 도로 관리에 도움이 될 것으로 사료된다.

구조방정식모형(SEM)을 활용한 중국 이혼율 영향 요인 분석 연구

후샤징(Xiajing Hu),김유정(You Jeong Kim),김준홍(Jun Hong Kim),최용석(Yong-Seok Choi) 한국자료분석학회 2022 Journal of the Korean Data Analysis Society Vol.24 No.6

본 연구는 세계 최대 인구 보유국인 중국이 최근 이혼 문제로 고심하고 있는 점을 고려해 급격하게 증가하고 있는 이혼율에 영향을 미치는 구체적인 요소를 파악하고자 하였다. 1987년 0.5 (‰, 1000명당 이혼 건수)였던 중국의 조이혼율(이하 이혼율로 통칭)은 2019년 3.4로 17년 연속상승하고 있는 추세를 보인다. 중국의 이혼율에 관한 연구는 다양하게 진행되어 왔으나 구조방정식모형을 활용한 연구는 다소 미흡한 상태이다. 이에 본 연구에서는 중국 전체 지역을 기준으로 이혼율에 미치는 영향을 파악하고 난 후 지역별로 이혼율 분포를 파악하여 이혼율이 높은 지역, 평균인 지역, 낮은 지역 간 이혼율 상승 원인과 지리적인 차이를 비교 분석하고자 한다. 이를 위해 National Bureau of Statistics of China, Global Data Lab 그리고 CEI Data의 오픈 자료로부터 중국의 2001년부터 2019년까지의 이혼율과 상관이 높은 GDP, 소비수준, 여성 수입 및 교육수준, 출산율 등의 총 12개 변수를 선택하였고, 기술통계분석, 다변량 분산분석(MANOVA)과 프로파일 분석(profile analysis, PA)을 통해 이혼율이 높은 지역(헤이룽장성:黑龍江), 평균 지역(산시성: 陝西), 낮은 지역(광둥성:廣東) 총 3개 집단 간에 차이가 있는지 확인하였다. 그리고 탐색적 요인분석을 통해 이혼율에 미치는 요인을 분석했다. 끝으로 구조방정식모형의 분석에서 이혼율이 높은 헤이룽장성과 평균인 산시성, 낮은 광둥성 간에 경제사회 개발화 특성 및 현대가족 특성이이혼율과 출산율에 미치는 영향을 검증하여 결론을 내리고자 한다. 따라서 본 연구에서 언급된영향 외에도 이혼율에 영향을 미치는 이유는 여러 가지 있을 것으로 여겨진다. In recent years, the divorce rate for China has been rising year by year. Based on the crude divorce rate from 2001 to 2019, this paper selects four groups of Heilongjiang, Shanxi and Guangdong, where the total divorce rate and the total divorce rate of China are high, medium and low respectively, and explores the reasons for the rising divorce rate of China from three aspects of economy, education and population composition. Compare the provinces with high divorce rate and low divorce rate at the same time, and analyze the reasons and geographical differences of rising divorce rate. This paper is mainly divided into two parts. The first part is the comparison of differences between four groups based on multivariate statistical analysis, and the second part is structural equation model analysis. The first part is mainly descriptive statistics and variance analysis of all groups in China, Shaanxi, Guangdong and Heilongjiang, to confirm whether there are differences among the four groups. Then, profile analysis was conducted to compare the whole in China and Shaanxi province with the median divorce rate, as well as heilongjiang Province with the high divorce rate and Guangdong Province with the low divorce rate. In the second part of structural equation model analysis, first of all, the factors affecting the divorce rate were analyzed. Secondly, through the structural equation model analysis, the effect of economic and social development characteristics and modernization characteristics and fertility on divorce rates between Heilongjiang Province, the average Shanxi Province, and low Guangdong Province is verified and concluded. Through a variety of analyses, this paper draws a conclusion that the divorce rate for China is greatly influenced by social development characteristics and modernization characteristics and fertility. However, there is little difference in the influence factors of the three provinces of China.

Variance components, correlation and path analyses in cowpea (Vigna unguiculata L., Walp)

Aliyu Olawale Mashood,Tiamiyu Adeyemi Odunola,Usman Muinat,Abdulkareem Yusuf Folorunsho 한국작물학회 2022 Journal of crop science and biotechnology Vol.25 No.2

Cowpea as a low-input crop has a potential to signifcantly ameliorate poor nutrition and food insecurity in sub-Sahara Africa if problem of poor seed yield is addressed. Adequate information on the relationship between yield components and seed yield is, however, crucial for the development of better quality varieties to improve farmers’ feld yield. To this end, twelve cowpea accessions of diferent seed sizes and mixed pedigrees were evaluated for two years in feld trials of three replications laid out in a randomized complete block design. Data collected on plant vigour indices, yield components and seed yield were analyzed for variance components, Pearson correlation coefcient and structural equation modeling for path analysis. The accessions exhibited signifcant variation for all yield components including seed yield. In addition, the variance estimates indicated that substantial variations recorded were mostly genetic with high heritability values. Earliness in fowering and pod maturity recorded highly signifcant correlations and direct efect with yield components and seed yield. Positive correlation between precocity and high yield could be exploited in the development of improved varieties with early maturity for the savannah ecology with a characteristic short wet season. Importantly, all seed yield components are signifcantly correlated with each other and to total seed yield. Pods per plant, however, recorded highest coefcient values (r=0.85; P<0.001; 1.38**) for both Pearson correlation and path analysis, respectively, suggesting its importance as a yield component with highest direct efect on seed yield and should be a core selection index in cowpea breeding. The efect of size-number trade-of accounts for the counter-balance of direct efects of seeds per pod/plant (number) and seed weight (size) in cowpea and should be determined on genotype and/or seed size basis during selection. Plant vigour characters had no direct contribution to seed yield.

농법 및 시기 변화에 따른 논토양의 환경 특성 분석

이태구(Tae-Gu Lee),박성직(Seong-Jik Park),이용호(Yong Ho Lee) 大韓環境工學會 2017 대한환경공학회지 Vol.39 No.6

본 연구에서는 농법 및 시기에 따른 논토양의 화학성을 비교 분석하였다. 이를 위하여 관행논 11개 필지와 유기논 24개 필지에 대하여 3월, 5월, 8월, 10월에 토양 시료 채취 및 분석을 수행하였고, 실험 분석 결과에 대해 통계 분석을 수행하였다. 분산분석 결과 농법에 의한 유의미한 차이가 나타난 항목은 NH4-N와 P2O5이었지만, 시기에 따른 차이는 모든 항목에서 높은 유의성 있는 차이를 보였다. 주성분 분석 결과 또한 토양내 질소 및 인의 농도는 농법에 의한 영향보다는 시료 채취시기에 따른 영향이 더 크게 나타났다. 토양의 전기전도도는 3월에서 10월로 감에 따라서 값이 증가하였다. 토양 유기물은 3월 및 5월에 비하여 8월과 10월에 높게 나타났다. T-N는 3월에서 10월로 지남에 따라서 감소하는 경향을 나타냈다. NH4-N 및 NO3-N 농도는 관행논 및 유기논 모두 5월에 가장 높게 나타났다. T-P 농도는 8월에 가장 높은 값을 나타낸 반면에, P2O5의 경우에는 8월에 가장 낮은 값을 나타내었다. 본 연구 결과 논토양의 화학적 특성은 농법에 의한 차이보다는 시기에 의한 차이가 더 크게 나타났다. 따라서 토양 환경 특성에 대한 분석 및 비교시 시기에 대한 고려가 반드시 필요한 것으로 판단된다. The aim of this study is to investigate the environmental properties of paddy soils depending on farming methods and seasonal variation. The paddy soils in 11 plots of conventional paddy and 24 plots of organic paddy were sampled and analyzed in four season of March, May, August, and October. The obtained data of soil properties were used for statistical analysis. Analysis of variance showed that only NH4-N and P2O5 were significantly different depending on farming methods. However, the differences of all soil properties depending on seasonal variation were strongly significant. Principal component analysis also presented that nitrogen and phosphorus concentration in soils were more significantly influenced by seasonal variation than farming method. Electric conductivity in soil was decreased from March to October. Amounts of soil organic matter in August and October were higher than that in March and May. T-N was decreased from March to October. NH4-N and NO3-N in the soil of both conventional and organic paddy were higher in May than other seasons. T-P concentration was found to be highest in August, but P2O5 concentration was lowest in August. It can be concluded that seasonal variation should be considered for analysis and comparison of soil environmental properties.

CENETIC ANALYSES BY THE DIALLEL CROSS IN F_2 GENERATION OF ADZUKI BEAN (Phaseolus angularis)

HAN, KYUNG SOO,KIM, SEOK HYEON,KIM. JIN HYEONG 경상대학교 유전공학연구소 1983 遺傳工學硏究所報 Vol.2 No.-

A set of 36 crosses of F_2 generation by 9×9 diallel crosses from nine adzuki bean varieties (Yeongdong Jeogdu, Gongju Baegdu, Gyeonggi Gaeguri, Wase Dairuyu No. 1, Natsu Adzki, Maruba No.1, Jeogdu, Nezumi Mochi and Hongcheon Jeogdu) were used as the materials, in the field trials for estimating genetic parameters such as gene action, combining ability and the relationships between parents and their F_2 hybrids. Experiments were conducted in 1982, and three agronomic characters, I. e., pod numbers per plant, 100-grain weight and grain weight per plant were observed. The F_2 generation of this diallel set of crosses was analysed for each character by Jinks', Hayman's and Griffing's methods. The results obtained are summarized as follows: 1. The Jinks and Hayman's (Vr-Wr) graphic analyses: Pod numbers per plant, 100-grain weight and grain weight per plant were found to be inherited in partial dominance. 2. Components of variance: Estimates of additive component of variance (D) were greater than those of dominance component of variance(H_1) for pod numbers per numbers per plant, 100-grain weight and grain weight per plant. Negative values of F were estimated for characters such as pod numbers per plant and grain weight per plant, which were interrupted as recessive allelomorphs. 3. Combining ability analyses: Mean squared of GCA(general combining ability) for all three characters, i.e., pod numbers per plant, 100-grain weight and grain weight per plant, were much higher than those of SCA(specific combining ability). 4. Effects of combining ability: Variety Gyeonggi Gaeguri was expressed as the high GCA effects for pod numbers per plant and grain weight per plant. SCA effects were different from parents and characters in the different crosses, but high SCA effects for pod numbers per plant and grain weight per plant were expressed in the cross between Yeongdong Jeogdu and Nezumi Mochi.

On the Admissibility of Hierarchical Bayes Estimators

김병휘,장인홍 한국통계학회 2006 Journal of the Korean Statistical Society Vol.35 No.3

In the problem of estimating the rror variance in the balanced xed-eects one-way analysis of variance (ANOVA) model, Ghosh (1994) pro-posed hierarchical Bayes estimators and raised a conjecture for which all ofhis hierarchical Bayes estimators are admissible. In this paper we prove thisconjecture is true by representing one-way ANOVA model to the distribu-tional form of a multiparameter exponential family.AMS 2000 subject classications.Primary 62C15; Secondary 62F10.Keywords.Error variance, multiparameter exponential family, one-way analysis of vari-ance model, relative squared error loss.1. IntroductionConsider the problem of estimating the rror varianceσ2 in the followingbalanced one-way analysis of variance (ANOVA) model:Yij = θi + .ij , i= 1 ,2,.,k, j = 1 ,2,.,n, (1.1)where the.ij ’s are independentely and identically distributediid as N(0,σ2).The loss to be considered is the relative squared error lossL(d,σ2) = (dσ2 1)2. (1.2)Ghosh (1994) developed the hierarchical priors and the corresponding hi-erarchical Bayes estimators ofσ2 and derived a subclass of these hierarchicalBayes timators which dominates the best multiple estimator ofσ2, namelyReceived October 2005; accepted July 2006.

Comparison of Sensitivity Analysis Methods for Building Energy Simulations in Early Design Phases: Once-at-a-time (OAT) vs. Variance-based Methods

김선혜 한국생태환경건축학회 2016 한국생태환경건축학회 논문집 Vol.16 No.2

Purpose: Sensitivity analysis offers a good guideline for designing energy conscious buildings, which is fitted to a specific building configuration. Sensitivity analysis is, however, still too expensive to be a part of regular design process. The One-at-a-time (OAT) is the most common and simplest sensitivity analysis method. This study aims to propose a reasonable ground that the OAT can be an alternative method for the variance-based method in some early design scenarios, while the variance-based method is known adequate for dealing with nonlinear response and the effect of interactions between input variables, which are most cases in building energy simulations. Method: A test model representing the early design phase is built in the DOE2 energy simulations. Then sensitivity ranks between the OAT and the Variance-based methods are compared at three U.S. sites. Result: Parameters in the upper rank by the OAT do not much differ from those by the Main effect index. Considering design practices that designers would chose the most energy saving design option first, this rank similarity between two methods seems to be acceptable in the early design phase.