A0564
Title: Propensity score with factor loadings: Evaluating the effect of the Paris agreement on the returns of European stocks
Authors: Angelo Forino - Sapienza University (Italy)
Giacomo Morelli - Sapienza University of Rome (Italy)
Andrea Mercatanti - Sapienza University of Rome (Italy) [presenting]
Abstract: Research in methods for policy evaluation has shown a growing interest in factor models for panel data where the policy adoption is unconfounded with respect to a low-dimensional set of latent factor loadings. A large part of this literature focused on comparative case analysis with only one or a few treated units under a causal finite-sample approach, which is, however, more suitable for inference from experimental than from observational studies. Motivated by the evaluation of the Paris Agreement, a policy aimed at fostering the transition to a low-carbon economy, on European stock returns, an inverse propensity score weighting approach is proposed under a super-population causal approach, where the propensity score is a function of the latent factor loadings. Moreover, the assumption is relaxed (common to the causal analysis of panel data) of the absence of anticipatory effects. Under standard assumptions regarding the latent factors structure, a three-step inferential procedure is outlined within the M-estimation framework that accounts for uncertainties both in the estimation of factor loadings and propensity scores. Simulation studies illustrate the performance of the proposed method. The empirical application does reveal a significant short-run effect of the Paris Agreement.
