Innovation performance evaluation for high-tech companies using a dynamic network data envelopment analysis approach

Abstract

This study examines innovation performance of high-tech companies in China, using a dynamic network data envelopment analysis (DEA) approach. The innovation process is decomposed into a research and development (R&D) stage and a commercialization stage. In addition, innovation is conceptualized as a consecutive event that goes through multiple time intervals, requiring a dynamic structure of the methodological framework. Using a newly developed dynamic network DEA, the current study calculates a R&D performance index and a commercialization index for the R&D stage and commercialization stage, respectively. The multi-process innovation system is integrated with dynamic carryover items. This results in a highly non-linear dynamic network DEA model. Second order cone programming and nested partitions strategies are employed to solve the nonlinear dynamic network DEA model. Our empirical study indicates disparities in innovation performance among different Chinese high-tech companies. The innovation heterogeneity and inefficient performance sources are also investigated.