[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

SEMINARIO Prof. J. Breitung - DSS Udine - 11 luglio



*******************************************************
			AVVISO DI SEMINARIO
*******************************************************

Il giorno giovedì 21 luglio 2005, ore 11.00, presso la
Sala Conferenze del Dipartimento di Scienze Statistiche
Via Treppo 18, Udine, il

	Prof. Joerg Breitung,
	Department of Economics, University of Bonn

terrà un seminario dal titolo:

Testing for Unit Roots in Panels With a Factor Structure

Abstract

This paper considers two simple tests for the unit root hypothesis in panels
where
the cross section dependence is due to a common factor structure. First, we
show that under
the null hypothesis of a unit root, the test based on the OLS regression
converges to a simple
functional of Brownian motions. Moreover, we note that under the null
hypothesis of unit
roots this test is asymptotically equivalent to a Dickey-Fuller test applied
to the first principal
components. Second, the test based on a GLS regression has a standard normal
limiting null
distribution. We also investigate the relationship to test statistics
recently suggested for panel
data with a factor structure. A Monte Carlo study is conducted to gauge the
small sample
performance of these tests and a panel data set of 16 countries is used to
test the hypothesis
that interest rates are stationary.




***************************************************
Tommaso Proietti
Dipartimento di Scienze Statistiche
Via Treppo 18, I-33100 Udine
http://www.dss.uniud.it/proietti/
***************************************************


=============================================================================
NOTA:
Le norme per utilizzare il forum SIS e le istruzioni per iscrizione
e cancellazione sono disponibili all'indirizzo
.
.   http://w3.uniroma1.it/sis/forum.asp
.
L'archivio di tutti i messaggi (aggiornato al giorno precedente)
e' disponibile all'indirizzo
.
.   http://www.stat.unipg.it/cgi-bin/wilma/sis/
.
=============================================================================