Bayesian Model Averaging in the Instrumental Variable Regression Model

This paper considers the instrumental variable regression model when there is uncertainty about the set of instruments, exogeneity restrictions, the validity of identifying restrictions and the set of exogenous regressors. This uncertainty can result in a huge number of models. To avoid statistical problems associated with standard model selection procedures, we develop a reversible jump Markov chain Monte Carlo algorithm that allows us to do Bayesian model averaging. The algorithm is very exible and can be easily adapted to analyze any of the di¤erent priors that have been proposed in the Bayesian instrumental variables literature. We show how to calculate the probability of any relevant restriction (e.g. the posterior probability that over-identifying restrictions hold) and discuss diagnostic checking using the posterior distribution of discrepancy vectors. We illustrate our methods in a returns-to-schooling application.

The Inventor Balance and the Functional Specialization in Global Inventive Activities

We study the functional specialization whereby some countries contribute relatively more inventors vs. organizations in the production of inventions at a global scale. We propose a conceptual framework to explain this type of functional specialization, which posits the presence of feedbacks between two distinct sub-systems, each one providing inventors and organizations. We quantify the phenomenon by means of a new metric, the “inventor balance”, which we compute using patent data. We show that the observed imbalances, which are often conspicuous, are determined by several factors: the innovativeness of a country relative to its level of economic development, relative factor endowments, the degree of technological specialization and, last, cultural traits. We argue that the “inventor balance” is a useful indicator for policy makers, and its routine analysis could lead to better informed innovation policies.