Economic Policy Uncertainty in Latin America: Measurement using Spanish Newspapers and Economic Spillovers

Abstract

The Working Paper Series seeks to disseminate original research in economics and fi nance. All papers have been anonymously refereed. By publishing these papers, the Banco de España aims to contribute to economic analysis and, in particular, to knowledge of the Spanish economy and its international environment. The opinions and analyses in the Working Paper Series are the responsibility of the authors and, therefore, do not necessarily coincide with those of the Banco de España or the Eurosystem. The Banco de España disseminates its main reports and most of its publications via the Internet at the following website: http://www.bde.es. Reproduction for educational and non-commercial purposes is permitted provided that the source is acknowledged.

The information content of conflict, social unrest and policy uncertainty measures for macroeconomic forecasting

“…The measurement of the different angles of ''institutional instability'', namely conflict (whether armed, or violence more broadly), social unrest, or policy uncertainty, has benefited dramatically from advancements in textual analysis, i.e. the use of machine learning algorithms to find topics or combination of relevant keywords in massive amounts of text related to the issues of interest Rauh, 2022a, 2018;Barrett et al, 2020;Ghirelli et al, 2021;Caldara and Iacovello, 2022).…”

“…They suggest that it is important to maximise the breadth of press coverage when building text-based indicators, since this improves the credibility of results. This is the reason why for the purpose of our exercise, instead of relying on the national EPU indicators available in www.policyuncertainty.com, we use a novel adaption of this method developed by Ghirelli et al (2019Ghirelli et al ( , 2021, constructed using major Spanish newspapers. This offers the advantage of a potentially less biased view of economic policy uncertainty, but comes at the expense of not being as readily available to a wider audience.…”

“…The modelling framework is the time-series mixed-frequency MIDAS approach. Three types of textbased indicators are incorporated into the models: (i) conflict risk, updated following Mueller and Rauh (2022a), that have been developed by applying a combination of supervised and unsupervised ML techniques over a wealth of news sources; (ii) economic policy uncertainty (EPU) indicators, taken from Ghirelli et al (2021), developed using supervised machine learning techniques, by means of computational text analysis applied to a wealth of Spanish newspaper sources; and (iii) other measures of socio-political conflict adopted from Barrett et al (2021) and Caldara and Iacovello (2022). In addition, we evaluate the usefulness of adding the more standard political risk indicators to the models, including those reflected in ratings of international agencies.…”

New Data Sources for Central Banks

“…By documenting the spillover effects of rising uncertainty across countries, the literature also demonstrates that rising economic uncertainty in one country can have global ramifications (e.g., [8,9,23,59]). In this respect, [39] develop Economic Policy Uncertainty indexes for the main Latin American (LA) countries: Argentina, Brazil, Chile, Colombia, Mexico, Peru, and Venezuela. The objective of constructing these indexes is twofold: first, to measure economic policy uncertainty in LA countries in order to get a narrative of "uncertainty shocks" and their potential effects on economic activity in LA countries, and second, to explore the extent to which those LA shocks have the potential to spillover to Spain.…”

“…In particular,(1) we require that each article also contains the name of the LA country of interest;(2) among the set of keywords related to policy, we include the name of the central bank and the name of the government's place of work in the country of interest. For more details, see[39].…”