Research seminar at Eesti Pank on 7 November

You are kindly invited to attend the Eesti Pankʼs research seminar in Webex on 7 November at 11:00 am. During this seminar, Francesca Loria (Board of Governors of the Federal Reserve System) will present on “Flexible Priors and Restrictions for Structural Vector Autoregressions”. 

This study introduces an innovative approach for estimating Bayesian vector autoregressions (VAR) in structural form, enhancing flexibility in incorporating various priors and identification strategies. The method accommodates zero, sign, and narrative restrictions, as well as identification via proxy variables, offering a unified framework for replicating prominent strategies in the VAR literature. Unlike existing methods, it directly elicits informative priors and restrictions on structural parameters, ensuring transparency and avoiding unintended beliefs. The approach is versatile, scalable to larger models and eliminates the need for separate algorithms for different identification schemes. By employing endogenous priors, it overcomes issues related to non-uniform priors over identified sets, extending beyond impulse responses. Additionally, the methodology allows for imposing (in-)equality restrictions on VAR parameters, providing a robust means to incorporate strong beliefs. Overall, this user-friendly framework addresses key challenges in the current literature, offering a valuable tool for empirical researchers, with the method accessible through the RISE toolbox.

Co-authors of the paper:
Christiane Baumeister (University of Notre Dame) and Junior Maih (Norges Bank)

Meeting information in Webex:
https://eestipank.webex.com/eestipank/j.php?MTID=mce3a338ee6164833d9cede1d167df727
Meeting number: 2741 483 6629
Password: dmTBJ3fNE82 (36825336, from phones and video systems)

Research seminar at Eesti Pank on 17 October

You are kindly invited to attend the Eesti Pankʼs research seminar in Webex on 17 October at 10:30 am, during which Georg Strasser (European Central Bank) will present on “Inflation heterogeneity across households.”

Systematic inflation differences between households have distributional and welfare effects. Moreover, individual past inflation experiences might affect inflation expectations, so that a heterogeneity of inflation realizations can entail a heterogeneity of inflation expectations. This paper examines inflation heterogeneity across households in France and Germany. It documents large and persistent inflation differences between households, decomposes these differences in price and basket components, and identifies their main drivers. The analysis is based on a large household panel reporting the purchases of fast moving consumer goods, i.e. of the products which households buy most frequently. This set of products is particularly relevant because households form their inflation expectations based on them. The GfK dataset covers German households during the years 2005–2018 and the Kantar dataset French households during 2008–2018, with purchases totalling more than 330 million and 145 million euro, respectively. Both panels contain prices, quantities, and product characteristics of the purchases of households together with some demographic information. This paper presents four key insights. First, income (and other standard demographic characteristics) explain little of the inflation differences between households. The key driver of inflation heterogeneity is household behaviour. Income plays an indirect role: as household behaviour is weakly correlated with income, at times significant inflation differences between income groups emerge. Second, household behaviour affects inflation heterogeneity mainly through product choice. While individual households might find lower prices for a given product, these price differences constitute only a small share of the overall inflation heterogeneity. Only price differences between larger regional units matter, e.g. a different price paid for the same product in a metropolitan region vs. a distant rural region. This translates into inflation heterogeneity at the regional level. Third, the households’ product choice within a category appears to be largely detached from the products’ relative price. In other words, households often substitute into a product whose relative price has increased. Fourth, the dispersion of household-level price indices based on a fixed ex-ante basket changes little when heterogeneous preferences across goods are introduced, and becomes even larger when allowing for time variation in preferences. These findings caution against focusing on income as the sole explanation of inflation heterogeneity among households. Instead, the main driver is household behaviour, in particular product choice. Therefore the heterogeneity of preferences– across goods and over time needs to be taken into account. Preference heterogeneity is also behind the often counterintuitive substitution patterns. In contrast, price search by households and the resulting differences in prices paid for identical products matter relatively little for inflation differences between households.

Co-author of the paper: Regina Kiss (University of Vienna)
ECB working paper: https://www.ecb.europa.eu/pub/pdf/scpwps/ecb.wp2898~29405f932f.en.pdf

Meeting information in Webex:
https://eestipank.webex.com/eestipank/j.php?MTID=m6ff154a8b55755b113c5b9352bab34d1
Meeting number: 2742 055 6638
Password: crC3EJaQP43 (27233527, from phones and video systems)

J.Stroinovskis lecture on 10 October

The third lecture of the J. Stroinovskis lecture series organized by the Bank of Lithuania and Vilnius University will take place on 10th October. Cecilia García Peñalosa (Aix-Marseille School of Economics, AMSE) will give a lecture on “The Dynamics of Lifetime Earnings” in the TechHub conference hall (2nd floor).

  • Time: October 10, 15.30-17.30
  • Venue: TechHub Conference Room (Saulėtekio al.9, 2nd building, 2nd floor)
  • Presenter: Cecilia García Peñalosa, Professor of Economics at the Aix-Marseille School of Economics
  • Topic: The Dynamics of Lifetime Earnings
  • Working language: English