Analysing inefficiency in a non‐parametric spatial‐dynamic by‐production framework: A <i>k</i>‐nearest neighbour proposal

Abstract This paper accounts for spatial effects by benchmarking farms against their k ‐nearest neighbours (KNN) and measuring inefficiency in a non‐parametric dynamic by‐production setting. The optimal number of which are compared corresponds to the value that maximises Moran I test autocorrelation good bad output farms' two sub‐technologies. scores output, variable inputs, investments outputs then computed with those calculated based on global technology, benchmarks all together. application focuses an unbalanced panel specialised Dutch dairy over period 2009–2016 contains information exact geographical locations. results suggest exhibit statistically significant differences between KNN model. Specifically, inefficiencies generally deflated when technology is considered, suggesting ignoring can overestimate inefficiency.