A1299
Title: Testing for differences in survey-based density expectations: a compositional data approach
Authors: Alexander Glas - FAU Erlangen-Nuernberg (Germany) [presenting]
Jonas Dovern - Heidelberg University (Germany)
Geoff Kenny - European Central Bank (Germany)
Abstract: Survey-based density expectations are proposed to be treated as compositional data when testing either for changes in density forecasts over time or for heterogeneity across different groups of forecasters. Monte Carlo simulations show that our test has more power relative to both a bootstrap approach based on the KLIC and an approach which involves multiple testing for differences of individual parts of the density. In addition, the test is much faster than the KLIC-based one since it does not rely on simulations and allows for comparisons across multiple groups. Using density expectations from the ECB Survey of Professional Forecasters and the U.S. Survey of Consumer Expectations, we show the usefulness of the test in detecting possible changes in density forecasts over time and across different types of forecasters.
