Super DEA에 의한 광고비의 효율성 측정

한동여,최성용 한국기업경영학회 2009 기업경영연구 Vol.16 No.4

Parametric approach or non-parametric approach is used to measure the efficiency of decision making units. The two approaches have advantages and disadvantages. One disadvantage of parametric approach is to measure the efficiency by comparing a decision making unit to an average rather than comparing to best decision making units. Moreover, the parametric model has to assume about the production function, and requires the price information about inputs and outputs. Data envelopment analysis does not require the assumption about the production function and the price information. Data envelopment analysis is to measure the efficiency by comparing a decision making unit to best decision making units similar to it. Therefore, data envelopment analysis provides inefficient decision making units with benchmarking decision making units. Another advantage of data envelopment analysis is to handle for multiple outputs as well as zero output. But the data envelopment analysis model is extremely sensitive to the outliers. Data Envelopment Analysis which is non-parametric approach is a useful tool to analyze the relative efficiency of decision making units characterized by multiple inputs and multiple outputs. From the DEA results, it is impossible to differentiate their performance among the efficient decision making units. Super data envelopment analysis can provide super efficiency scores for all efficient decision making units. Therefore, we can rank the efficient decision making units. The super efficiency of decision making unit under consideration is estimated by excluding the constraints from traditional DEA model. Data envelopment analysis has been popularly used as an analytical tool in order to evaluate relative performance of decision making units. The results of Data envelopment analysis model provide decision makers with a single efficiency score, efficient frontier, return to scale, benchmarking decision making units for inefficient decision making units, etc. The purpose of this paper is to estimate advertising efficiency for the food and beverage companies in 2008 by super data envelopment analysis. Four items such as TV advertising expenditures, radio advertising expenditures, newspaper advertising expenditures, and magazine advertising expenditures are selected as inputs, and sales are treated as outputs for data envelopment analysis model. Super DEA model based on the input-output shows that 4 decision making units(DMU 2, DMU 5, DMU 6, DMU 10) are efficient out of 10 companies. The super DEA scores for DMU 2, DMU 5, and DMU 10 are 1.7073, 5.0898, 2.5814 and 1.4232 respectively. The results indicate that DMU 5(5.0898) is the most efficient. The score of 5.0898 means that DMU 5 can maintain 100% efficient even if DMU 5 increase inputs about 400%(5.0898-1). Furthermore, pure technical efficiency and scale efficiency are estimated for all DMUs. Constant return to DEA model shows that all inefficient decision making units should decrease their advertising expenditures in order to be efficient. In addition, we calculate the economies of scale such as increasing return to scale, decreasing return to scale, and constant return to scale for all decision making units from CRS DEA model. Based on the analysis of the economies of scale, this study recommends that decision making units with increasing return to scale can increase outputs by increasing advertising expenditures because decrease in advertising expenditures may not be possible due to various reasons in the real situation. Our analysis shows that 4 DMUs are under constant return to scale, 5 DMUs under increasing return to scale, and 1 DMU under decreasing return to scale, Decision making units under constant return to scale is now efficient by increasing output since the output will increase equally with the increase in advertising expenditures. 5 decision making units under increasing return to scale indicate that its efficiency can be improved by increasing a... 본 연구는 Super DEA기법에 의하여 2008년도 우리나라 식, 음료관련 기업의 광고 효율성을 측정하였다. 투입요소로는 TV광고비, 라디오광고비, 신문광고비, 잡지광고비로 하고 산출물은 매출로 하였다. 여기에서는 비효율적 DMU의 벤치마킹 대상 DMU와 과다 투입된 투입요소의 크기, 규모의 경제분석 결과 및 효율적 DMU들 간에 순위비교가 가능하도록 정보를 제공하였다. 본 연구에서는 비효율적 DMU가 효율적이 되기 위해서는 광고비를 축소해야 한다는 것을 보여주었지만, 동시에 비효율적인 DMU들은 상당수가 IRS에 있음을 확인하였다. 비효율적인 광고주가 광고비를 축소하여 효율적이 될 수도 있지만 상당수의 DMU들이 규모수익 증가에 있기 때문에 광고비를 축소하기 보다는 광고비를 증가시키거나 기존의 광고비 비율을 유지하면서 광고효율성을 제고할 수 있음을 발견하였다.

공공조직의 순위 평가 방안: 확률적 변경분석과 자료포락분석의 적용

정수관,원두환 한국자료분석학회 2014 Journal of the Korean Data Analysis Society Vol.16 No.6

Stochastic frontier analysis and data envelopment analysis are widely used for ranking evaluating in efficiency of public institute performance, and most previous research have measured efficiency and ranking evaluation by an analysis method. However, decision-makers are interested in efficiency ranking in order to support selective parts, but they can be confused with the differences in ranking evaluation by analysis methods. This study shed light on the complimentariness in stochastic frontier analysis and data envelopment analysis in ranking evaluation. Return to scale in efficiency of public institute is tested by stochastic frontier analysis. Then, a type of data envelopment analysis is determined by the result of return to scale. The differences of evaluation ranking between two analysis are examined. We find that the ranking order in efficiency is significant differences between the analysis and suggest a weighted average of two ranking evaluation as an alternative efficiency ranking. The method can be applied to other public areas. 공공조직의 성과를 평가하기 위해 확률적 변경분석과 자료포락분석이 많이 활용되고 있는데, 대부분의 연구는 각각의 분석법을 이용하여 효율성 측정에만 집중하였다. 그러나 두 가지 분석법은 장단점이 있기 때문에 각 방법의 특성을 이해하고 보완한다면 효율성 측정의 정확성을 향상시킬 수 있다. 본 연구는 확률적 변경분석과 자료포락분석을 이용하여 효율성을 각각 평가하고 두 결과를 보완하고자 한다. 이를 위해 부산시 28개 공공도서관을 사례로 효율성을 측정하였다. 먼저, 확률적 변경분석에서는 공공도서관의 투입-산출 변수를 이용하여 규모수익을 검증하고, 도서관의 효율성을 측정한다. 둘째, 확률적 변경분석의 결과를 통해 규모수익여부에 따라 적합한 자료포락분석을 선택한 후 개별 도서관의 효율성을 측정한다. 셋째, 자료포락분석의 모형 선택이 잘못되었을 경우에 효율성을 측정하고 비교하여, 확률적 변경분석을 통해 규모수익 확인의 중요성을 보인다. 마지막으로 분석방법의 차이점을 이해하고 각 분석을 통해 추정된 효율성에 가중평균을 이용하여 새로운 효율성 지표를 만들고자 한다. 분석결과 확률적 변경분석을 통해 부산시 공공도서관의 효율성은 규모수익체증이 나타남을 알 수 있었고, 규모수익을 고려하지 않은 자료포락분석은 효율성과는 측정에 왜곡이 발생하였다. 또한 확률적 변경분석과 자료포락분석에서 추정된 각각의 효율성을 가중평균하여 새로운 효율적 지표로 사용할 수 있다. 이러한 평가방안은 공공도서관을 포함한 다양한 공공조직의 효율성 측정에 응용할 수 있을 것이다.

자료포락분석에 의한 정부기관과 아웃소싱기관의 성과측정방법

유금록 한국지역발전학회 2007 지역발전연구 Vol.7 No.1

This paper deals with a method of measuring and comparing the performance of government and outsourcing agencies using data envelopment analysis. Data envelopment analysis is a promising method as an alternative to ratio analysis and regression analysis that have been used as tools for performance measurement. Data envelopment analysis measures the relative efficiency of decision-making units, and especially can be used for performance measurement of the public sector. This article explains the usefulness of data envelopment analysis, methods of building linear programming model through the multiplier model and envelopment model, and then suggests methods of measuring and evaluating the relative performance of government and outsourcing agencies using an illustrative example.

부정확한 데이터를 가지는 자료포락분석을 위한 로버스트 최적화 모형의 적용

임성묵(Sung mook Lim) 한국산업경영시스템학회 2015 한국산업경영시스템학회지 Vol.38 No.4

Conventional data envelopment analysis (DEA) models require that inputs and outputs are given as crisp values. Very often, however, some of inputs and outputs are given as imprecise data where they are only known to lie within bounded intervals. While a typical approach to addressing this situation for optimization models such as DEA is to conduct sensitivity analysis, it provides only a limited ex-post measure against the data imprecision. Robust optimization provides a more effective ex-ante measure where the data imprecision is directly incorporated into the model. This study aims to apply robust optimization approach to DEA models with imprecise data. Based upon a recently developed robust optimization framework which allows a flexible adjustment of the level of conservatism, we propose two robust optimization DEA model formulations with imprecise data; multiplier and envelopment models. We demonstrate that the two models consider different risks regarding imprecise efficiency scores, and that the existing DEA models with imprecise data are special cases of the proposed models. We show that the robust optimization for the multiplier DEA model considers the risk that estimated efficiency scores exceed true values, while the one for the envelopment DEA model deals with the risk that estimated efficiency scores fall short of true values. We also show that efficiency scores stratified in terms of probabilistic bounds of constraint violations can be obtained from the proposed models. We finally illustrate the proposed approach using a sample data set and show how the results can be used for ranking DMUs.

지방의료원의 성과분석: Data Envelopment Analysis와 패널분석

정은영 ( Eun Young Chung ),서영준 ( Young Jun Seo ),이해종 ( Hae Jong Lee ) 한국보건행정학회 2015 보건행정학회지 Vol.25 No.4

This study aims to examine the performance of public municipal hospitals through the analysis of data envelopment analysis, efficiency, profitability, and publicness by using panel data during period from 2006 to 2010. The main findings of the study are as follows. First, as a result of efficiency analysis during the period from 2006 to 2010, it was revealed that the number of staff by each job category, labor cost ratio, the number of operating beds need to be decreased. Second, the performance data represented by the indicators of efficiency, profitability and publicness were complementary and showed a tendency of being increased or decreased in same direction. Third, from the result of panel analysis, the efficiency was mainly influenced by the structural factors, while the profitability was influenced by managerial factors, and the publicness by medical environment. In conclusion, in order to enhance the performance of public municipal hospitals in Korea, it is important to harmonize the effort for effic ency, financial and policy support by central and local government, and the continuous participation of community residents.

제품효율성 분석을 통한 친환경자동차 시장의 활성화 방안 연구

이동우(Dongwoo Lee),오인하(Inha Oh) 한국혁신학회 2021 한국혁신학회지 Vol.16 No.3

본 연구의 목적은 DEA(Data Envelopment Analysis)를 활용한 제품효율성 분석을 통해 국내 친환경자동차 시장의 활성화 제고 방안을 모색하고자 함이다. 이를 위해 본 연구에서는 친환경자동차의 대상을 전기자동차와 하이브리드, 플러그인하이브리드 그리고 LPG자동차로 정하고 분석에 사용하였다. 연구자료는 한국자동차산업협회의 생산판매통계를 통해 2015년부터 2018년까지 국내 시장에서 판매된 일반 승용차와 2019년 일반인 판매대상의 LPG차량 자료를 활용하였다. 분석에 사용된 투입변수는 차량가격이며, 산출변수로는 환산연비, 엔진성능, 차체크기 그리고 가솔린, 하이브리드, SUV를 나타내는 더미변수가 사용되었다. 연구의 주요 내용을 요약하면, 첫째, 제품효율성 측정지표의 유용성 검증을 위해 기술적 효율성과 배분적 효율성 모델을 비교 분석하였는데, IV로짓 모형을 활용한 2SLS(Two-Stage Least Squares) 분석을 통해 소비자에게 주는 효용의 가중치를 추정하고 배분적 효율성 측정에 활용하였다. 둘째, 국내 자동차 시장의 소비유형별 배경변인에 따른 제품효율성 차이 여부를 알아보기 위해 비모수 검정을 실시하였다. 셋째, 투입 및 산출변수의 각 측정지표별 비교자료를 추출한 후, 시장점유율이 가장 높은 내연기관 가솔린 차종과의 상세 비교를 통해 각 친환경 차종과의 경제적 차이를 비교 분석하였다. 본 연구는 효율성 측정지표로서 배분적 효율성을 활용한 제품효율성이 국내 자동차 시장의 효율성을 설명하는데 보다 유용한 척도임을 검증하고, 이를 통해 제품의 소비자 관점에서 효율성을 분석하였다는 점에 의의를 둘 수 있다. The purpose of this study is to evaluate product efficiency with the domestic eco-friendly vehicles to which attention is paid as next-generation vehicles, utilizing Data Envelopment Analysis (DEA) and present measures for securing the development direction and competitiveness of the domestic eco-friendly vehicle industry through this. This study included eco-friendly vehicles, including electric vehicles, hybrid vehicles, plug-in hybrid vehicles, and Liquefied Petroleum Gas (LPG) vehicles for the analysis. As for research data, with the domestic cars sold in the South Korean vehicle market, this study added and utilized data on general passenger cars sold from 2015 through 2018 and LPG vehicles sold for ordinary people in 2019 through the production and selling statistics of the Korea Automobile Manufacturers Association (KAMA) for the analysis. The input variable used for DEA analysis was car price. As output variables, converted fuel efficiency, engine power, and car body volume were used, and dummy variables indicating gasoline, hybrid, and Sport Utility Vehicle (SUV) were used. The results of empirical analysis in this study are as follows: First, to verify the usefulness of the indicator for measuring efficiency for the evaluation of the product efficiency of eco-friendly vehicles, this study conducted a comparative analysis of the technical efficiency model and allocative efficiency model based on the DEA model. To do so, this study estimated the weighted value of the efficacy given to consumers through Two-Stage Least Squares (2SLS) analysis utilizing the IV Logit model and utilized that in the measurement of allocative efficiency. Second, to examine if there is any difference in product efficiency according to the background variable by the type of consumption in the domestic vehicle market, a non-parametric approach was made. Third, This study extracted data by each measurement indicator of the input variable and output variables for the comparisons of all models of vehicles in detail by class and type and then conducted a comparative analysis of the prices in detail with the gasoline models occupying the largest proportion of sales as internal combustion vehicle models in the domestic vehicle market, utilizing them. Through this, this study conducted a comparative analysis of the economic differences with gasoline models by each model of eco-friendly vehicles. This study has a significance that it verified if the product efficiency utilizing the allocative efficiency of the DEA model would be a more useful scale to explain the efficiency of the domestic vehicle market and analyzed the efficiency from the consumer point of view through that.

성과평가를 위한 자료포락분석에 있어서 쌍대이론에 의한 포락모형의 공식화와 적용

유금록(Keum-Rok Yoo) 한국정책분석평가학회 2007 政策分析評價學會報 Vol.17 No.4

  This study suggested linear programming models of the multiplier model and the envelopment model in data envelopment analysis for evaluating the performance of government and public agencies, and measured the efficiency of the twenty-five public health centers in Seoul metropolitan city districts using the output-oriented envelopment model. In particular, this paper suggested how to derive the envelopment model, the dual problem of the multiplier model, through the duality theory using linear programming models, because the envelopment model provides the advantages of providing various and useful management informations for inefficient agencies to benchmark efficient agencies as well as being easy to calculate, and the advanced theories of data envelopment analysis develops based on the envelopment form of data envelopment analysis.   The envelopment model of data envelopment analysis suggested in this article can apply to the evaluation of government services based on the Government Services Evaluation Act being enforced on and after April 1, 2006, and also contribute to the managerial evaluation of public agencies including public enterprises, quasi-government agencies and other public agencies by the Law of Public Agency Management taking effect on and after April 1, 2007.

자료포락분석을 이용한 아웃소싱업무의 효율성 평가

유금록 한국자치행정학회 2008 한국자치행정학보 Vol.22 No.1

본 연구에서는 자료포락분석을 사용하여 공공서비스의 효율성을 측정한 주요 선행연구들을 고찰한 후, 현대적 상대적 효율성 측정방법인 투입지향적 규모수익불변 및 규모수익가변 자료포락분석모형에 관한 선형계획모형을 공식화하고 아웃소싱업무의 효율성점수와 준거집단, 비효율성의 정도 및 근원 등을 분석했다. 본 연구결과의 시사점을 제시하면 다음과 같다. 첫째, 아웃소싱업무의 효율성 평가를 과학적으로 수행하기 위해서는 자료포락분석을 사용할 필요가 있다. 둘째, 자료포락분석을 이용하여 공공부문의 효율성을 분석한 기존의 선행연구들이 거의 대부분 횡단면자료를 사용했으나, 본 연구는 시계열자료를 사용하여 효율성을 측정할 수 있다는 점을 보여주고 있다. 셋째, 아웃소싱업무의 비효율성의 근원을 분석하기 위해서는 기술적 효율성을 기술적 순효율성과 규모효율성으로 구분하여 측정할 필요가 있다. An Efficiency Evaluation of Outsourced Government Services Using Data Envelopment Analysis Yoo, Keum-Rok This paper reviewed major previous studies measuring the efficiency of the public sector with data envelopment analysis (DEA), and then formulated the linear programming models of input-oriented constant returns to scale (CRS) and variable returns to scale (VRS) data envelopment analysis, one of modern efficiency measurement methods, and analyzed the efficiency scores, reference set, and inefficient amount and sources of an outsourced government service. The implications of this article are as follows. First, we need to use data envelopment analysis to scientifically perform the efficiency evaluation of outsourcing contract services. Second, this paper shows an efficiency measurement using time-series data, even though most existing research through data envelopment analysis uses cross-sectional data. Third, we need to measure the technical efficiency of outsourced government services and then decompose it into pure technical efficiency and scale efficiency to analyze sources of their inefficiency.

Data Envelopment Analysis (DEA)를 활용한 국내 커피전문점 기업의 상대적 경영 효율성에 관한 연구

안재형,최병철,김승범 한국외식경영학회 2019 외식경영연구 Vol.22 No.1

다양한 사회경제적 요인의 변화를 바탕으로 국내 커피소비량은 꾸준한 증가세를 보여 왔다. 이러한 현상에 힘입어 국내 프랜차이즈 커피전문점 시장 역시 급격한 성장세를 이어왔지만, 최근 들어 심화되는 경쟁 환경 속에서 이들의 생존과 경쟁력을 고민하는 연구들이 활발하게 진행되고 있다. 기존의 연구들이 주로 서비스의 품질, 소비자의 만족도, 해외 브랜드와 국내 브랜드 비교, 시장 포지셔닝 전략 등에 주초점이 맞추어서 진행되어온 반면, 본 연구는 국내 프랜차이즈 커피전문점의 ‘경영효율성’에 중심을 두고 연구를 진행한다. 이를 위해 Data Envelopment Analysis(DEA)기법을 활용하여 국내 대표적인 프랜차이즈 커피전문점 5개사의 ‘투입 대비 산출 효율성’을 측정하고 순위를 부여한 후 분석을 진행한다. 투입변수로는 업력, 매장수, 임직원수, 광고/판촉비, (기준)점포면적을 지정하였으며, 산출변수로는 매출액과 선호도를 산출변수를 지정하였다. 분석 결과 각 기업의 효율성을 확인할 수 있었으며, 과도한 투입이 이루어진 요소를 검증 할 수 있었다. 가장 효율성이 높은 업체로는 빽다방이 선정되었다. 현재 과다 경쟁으로 인하여 효율성이 저하되고 있는 프랜차이즈 커피전문점 시장에 대하여 객관적 분석에 기반을 둔 의미 있는 경영효율성 개선방향을 제공하였다는 점에 본 연구의 의의가 있다. This study aims to estimate the relative management efficiency of franchises coffee companies in Korea. While previous literature has mainly focused on estimating service quality and investigating strategic aspects of management, by using DEA analysis, we focus on comparing the relative management efficiency of five major franchise coffee companies in Korea. Through demonstrating the existence and importance of relative management efficiency among franchise coffee companies, our study contributes to the literature on franchise coffee business. Our contribution is that we have provided direction for the companies who are suffering from competition to improve their efficiency based on objective analysis.

Technical Efficiency of Professional Soccer Players in Europe -Using English Premier League Data-

( Tae Ho Kim ),( Seung Min Song ) 한국EU학회 2007 EU학연구 Vol.12 No.1

This paper proposes a scheme to estimate the technical efficiency of sports players as performance measure by Data Envelopment Analysis (DEA), to search for benchmark players by using technical efficiency, relative distance analysis, and frequency used as comparators analysis, and to identify factors which affect the technical efficiency by a kind of regression analysis. The result of technical efficiency estimation shows that there exists a substantial opportunity for improvement in technical efficiency of players and also the heterogeneity in the technical efficiency among players playing in the English Premier League. Benchmarking analysis gives us 7 benchmarks for inefficient players. Double limit Tobit analysis shows that age, height, salary of players affect the technical efficiency of players and winning point and the size of attendance of players` team also affect the technical efficiency of players. However, nationality, staying year in current team, remaining contract year do not affect technical efficiency.