Production Efficiency of Raw Milk and Its Determinants: Application of Combining Data Envelopment Analysis and Stochastic Frontier Analysis

China’s raw milk production is confronted with problems such as high costs, stringent environmental constraints, weak industrial interest linkages, etc. The extensive and inefficient operation mode seriously restricts the further development of dairy industry. How to increase efficiency realize transition from “a country production” high-efficiency has become key developing In order explore upgrading path industry in China, this study used DEA-Malmquist model estimate China analyze its spatial temporal distribution characteristics based on input output data at four scales (i.e., free-range, small-scale, medium-scale, large-scale) 2004 2020. It then adopted SFA relationship between factors driving efficiency. Finally, robustness was discussed according existing research differences. draws several valuable conclusions. First, 2020 fluctuated upward showed specific regular regional characteristics, but spatial–temporal differences were minor. Second, significantly influenced by various factors, including proportion concentrate roughage consumption, medical epidemic prevention investment, price milk, wage level, fixed assets. Third, are less robust, so analysis improvement measures should fully consider analytical methods, scale heterogeneity, indicator systems, heterogeneity.