Analysis of some portfolio selection models for R&D

This paper presents an analytical review of mathematical programming models that have been proposed as aids to the related problems of resource allocation and project selection in R&D. The models are classified according to whether they are based on linear, integer, chance constrained, or dynamic programming. Representative examples from these classes are described and evaluated in detail. The evaluation is in terms of data requirements; built-in assumptions; ease of computation; usefulness of outputs; versatility of application.