5. Conclusions
There are many opportunities for using descriptive, predictive and prescriptive modelling approaches in P/SM research. In today's research, studies often conduct tests that are only incremental changes to previous research and may not be based on any observed phenomenon in the business world. Therefore, empirical methods are needed to identify the model parameters and drive the experimental agenda for predictive and prescriptive models. One way to do this is to use a multi-method approach where an empirical case study or survey is used to gain insight into practice, and the results are used to frame the testing in a model that follows. Such empirically driven models have the potential to make significant contributions in P/SM research and a number of indicative research areas are provided in Table 1. Also in the context of the P/SM themes classification presented in Fig. 1 and in conjunction with the indicative research areas proposed in Table 1, future P/SM research needs to explore the value of modelling not just at the functional or operational level, but also at the organisation and strategic level respectively.