Chile Monthly Index

Download Data

We are pleased to host two new EPU indices for Chile developed by Rodrigo Cerda, Alvaro Silva and Jose Tomas Valente in "Economic Policy Uncertainty Indices for Chile".

Their indices reflect frequency counts of articles published in two Chilean newspapers, El Mercurio and La Segunda, from January 1993 to the present. They follow the index construction methods in "Measuring Economic Policy Uncertainty" by Scott R. Baker, Nicholas Bloom and Steven J. Davis.

As a small open economy, Chile is heavily exposed to the world economy, and Chilean newspapers carry many articles about economic matters that are not necessarily domestically related. Thus Cerda et al. construct two indices: one that considers articles pertaining to economic policy uncertainty, and another that considers the subset of articles pertaining to domestic Chilean sources of economic policy uncertainty. They label the first index as EPU and the second as EPUC in their annotated chart.

To construct their EPU index, Cerda et al. first obtain monthly counts of articles that contain term pertaining to uncertainty (incierto or incertidumbre), and economics (economía or económico/a or economista/s) and one or more of the following policy-relevant terms: politics (política) or tax (impuesto/s) or regulation (regulación) or tax collection (recaudación) or reform (reforma) or congress (congreso) or senate (senado) or congressman (diputado/a) or fiscal spending (gasto fiscal) or public spending (gasto público) or public debt (deuda publica) or fiscal budget (presupuesto fiscal) or Central Bank (Banco Central) or Ministry of Finance (Ministerio de Hacienda). After obtaining these raw counts, they scale by the number of articles published in the same newspaper and month. They standardize each newspaper's scaled frequency counts to have a unit standard deviation from January 1993 to October 2016, and then compute the simple average across newspapers by month. Finally, they multiplicatively normalize the series to have a mean of 100 from January 1993 to October 2016.

To construct their EPUC index, they require an article to also contain Chile or Chileno or Chilena in the first step. They then scale the raw frequency counts, standardize, average across newspapers by month, and normalize the resulting index in the same manner as for their EPU index.