Paper published in Journal of Choice Modelling on tools in the specification of a portfolio choice model
A paper has been published on PVE in Journal of Choice Modelling called "Data-driven assisted model specification for complex choice experiments data: Association rules learning and random forests for Participatory Value Evaluation experiments" written by José Ignacio Hernández, Sander van Cranenburgh and Niek Mouter.
In the last years, Participatory Value Evaluation (PVE) choice experiments have become an alternative to capture more complex and realistic forms of human decision making in diverse fields. While PVE choice experiments offer a more realistic experimental setting than a conventional DCE, specifying choice models to analyse data from such experiments is challenging. In the last years, there has been an increasing interest on assisting the specification of choice models with data-driven methods.
In this paper, three procedures are proposed based on association rules (AR) learning and random forests (RF) to support the specification of a portfolio choice model applied in data from complex choice experiment data, specifically a Participatory Value Evaluation (PVE) choice experiment. A methodological-iterative (MI) procedure is combined with AR learning and RF models to support the specification of parameters of a portfolio choice model. Additionally, RF model predictions are used to contrast the validity of the behavioural assumptions of different specifications of the portfolio choice model. The data of a PVE choice experiment is used to elicit the preferences of Dutch citizens for lifting COVID-19 measures.
The results show model fit and interpretation improvements in the portfolio choice model, compared with conventional model specifications. Additionally, guidelines are provided on the use of outcomes from AR learning and RF models from a choice modelling perspective.