Learning and heterogeneity in GDP and inflation forecasts
Using a Bayesian learning model with heterogeneity across agents, our study aims to identify the relative importance of alternative pathways through which professional forecasters disagree and reach consensus on the term structure of inflation and real GDP forecasts, resulting in different patterns of forecast accuracy. There are two primary sources of forecast disagreement in our model: differences in prior beliefs, and differences in the interpretation of new public information. Estimated model parameters, together with two separate case studies on (i) the dynamics of forecast disagreement in the aftermath of the 9/11 terrorist attack in the US, and (ii) the successful inflation targeting experience of Italy after 1997, firmly establish the importance of these two pathways to expert disagreement, and help to explain the relative forecasting accuracy of these two macroeconomic variables.
Year of publication: |
2010
|
---|---|
Authors: | Lahiri, Kajal ; Sheng, Xuguang |
Published in: |
International Journal of Forecasting. - Elsevier, ISSN 0169-2070. - Vol. 26.2010, 2, p. 265-292
|
Publisher: |
Elsevier |
Keywords: | Bayesian learning Public information Panel data Forecast disagreement Forecast horizon Forecast efficiency GDP Inflation targeting |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Measuring forecast uncertainty by disagreement: The missing link
Lahiri, Kajal, (2010)
-
Measuring Uncertainty of a Combined Forecast and Some Tests for Forecaster Heterogeneity
Lahiri, Kajal, (2015)
-
Measuring Forecast Uncertainty by Disagreement: The Missing Link
Lahiri, Kajal, (2008)
- More ...