Bayesian selection of technology assumptions for the transformation from supply-use to input–output tables

Abstract

In the construction of input-output models from supply-use tables, technology assumptions disambiguate how an industry uses inputs in the production recipe of multiple outputs. This paper uses Bayes' theorem to select technology assumptions, taking into account empirical observations. The paper presents a formulation to explore hybrids between product and industry technology assumptions in product-by-product tables. We then present Markov chain Monte-Carlo techniques to implement the Bayesian method for selecting technology assumptions. We apply the method in a case study using Eurostat supply-use tables of 2004 and 2005, exhibiting a volume of secondary products of less than 13%, and 59 products and industries per country. The results show that the choice of technology is not important, given that there is no strong evidence in favour of any of them.

Bayesian input–output table update using a benchmark LASSO prior

“…Moreover, we want to estimate/update the IO table elements, not multipliers. In this vein, related studies include those by Rodrigues, Amores and Paulo (2019), Torres-González and (2019), and Valderas-Jaramillo et al (2019…”