Measuring the efficiency of the Portuguese public hospitals: A value modelled network data envelopment analysis with simulation

In contrast to conventional data envelopment analysis (DEA), where a system is considered as a "black-box", network DEA acknowledges its internal structure to generate more enlightening results. It goes without saying that putting network DEA in practice is natural-and progressively rarer as the complexity of a system's structure increases. In particular, its employment in healthcare is no exception. Thus, we designed a slacks based model to measure the efficiency of the Portuguese secondary healthcare providers bearing in mind their internal services. However, the absence of data regarding the connections between those services called for the additional use of a simulation method - the well-known Monte Carlo method -, modelled with the judgements of a decision-maker. This unprecedented application of static systems with a matrix-type structure found that two-thirds of those providers were inefficient and allowed the identification of target areas for future policy reforms in the Portuguese National Health Service.