LocalitàRoom BZ E4.23, Universitätsplatz 1 - Piazza Università, 1, 39100 Bozen-Bolzano
Dipartimenti Press and Events
Contatto Sabine Zanin
SchoolofEconomics@unibz.it
29 gen 2018 12:30-13:30
Density Forecasts in Panel Data Models: A Semiparametric Bayesian Perspective
Laura Liu, Federal Reserve Board, Washington
LocalitàRoom BZ E4.23, Universitätsplatz 1 - Piazza Università, 1, 39100 Bozen-Bolzano
Dipartimenti Press and Events
Contatto Sabine Zanin
SchoolofEconomics@unibz.it
Here is the link tothe paper: http://laurayuliu.com/research/Working_Papers/Panel_Dfcst/panel_dfcst_paper.pdf
Abstract: This paper constructs individual-specific density forecasts for a dynamic panel data model with common and heterogeneous coefficients and cross-sectional heteroskedasticity. Due to the short time dimension, traditional methods have difficulty in disentangling the heterogeneous parameters from the shocks, which contaminates the estimates of the heterogeneous parameters. To tackle this problem, I assume that there is an underlying distribution of heterogeneous parameters, model this distribution non-parametrically allowing for correlated random effects, and then estimate this distribution by pooling the information from the whole cross-section together.