DEA를 이용한 수산양식업 효율성의 비교분석에 관한 연구

Abstract

The purpose of this study is to investigate production efficiency of various Korean aquaculture species using Data Envelopment Analysis. The study extracts 18 fishes in sea cage culture, 8 in aquarium basin, and 7 in enclosed aquaculture for its analytical purpose. First, the study estimates technical, pure technical, and scale efficiency of each aquaculture species based on traditional DEA under the assumptions of CRS and VRS. 10 fishes are identified as efficient DMUs under the CCR-model, and 15 under the BCC-model. We provide inputs that allow inefficient fishes to be efficient DMUs on a production frontier, and a reference set for their bench-marking. The study obtains a 95% confidence interval for each fish. By incorporating kernel density estimation and reflection method, the analysis uses smoothed bootstraping method in the process of resampling. While previous studies suffer from bias in the process of solving linear programming with the deterministic nature of production frontier, our research manages to estimate the bias-corrected efficiency scores. Hence, we can distinguish the order of efficient DMUs, which was actually impossible in the traditional-DEA. We have identified that puffers in aquarium basin are the most efficiently produced in both technical and pure technical efficiency. This result holds for both cases when the efficiency scores are adjusted with or without bias. Also we managed to measure the inefficiency which exists in efficiently produced fishes(in aquaculture production) when estimating the bias corrected efficiency scores.