"Reverse engineering" research portfolio synergies and tradeoffs from domain expertise in minimum data contexts

In research portfolio planning contexts, an estimate of research policy and project synergies/tradeoffs (i.e. covariances) is essential to the optimal leveraging of institution resources. The data by which to make such estimates generally do not exist. Research institutions may often draw on domain expertise to fill this gap, but it is not clear how such ad hoc information can be quantified and fed into an optimal resource allocation workflow. Drawing on principal components analysis, I propose a method for "reverse engineering" synergies/tradeoffs from domain expertise at both the policy and project level. I discuss extensions to other problems and detail how the method can be fed into a research portfolio optimization workflow. I also briefly discuss the relevance of the proposed method in the context of the currently toxic relations between research communities and the donors that fund them.