BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Identifying Cointegration by Eigenanalysis - Qiwei Yao — London 
 School of Economics
DTSTART:20191108T140000Z
DTEND:20191108T150000Z
UID:TALK130024@talks.cam.ac.uk
CONTACT:Dr Sergio Bacallado
DESCRIPTION:We propose a new and easy-to-use method for identifying cointe
 grated\ncomponents of nonstationary time series\, consisting of an eigenan
 alysis\nfor a certain non-negative definite matrix. Our setting is model-f
 ree\,\nand we allow the integer-valued integration orders of the observabl
 e\nseries to be unknown\, and to possibly differ. Consistency of estimates
 \nof the cointegration space and cointegration rank is established both\nw
 hen the dimension of the observable time series is fixed as sample size\ni
 ncreases\, and when it diverges slowly. The proposed methodology is also\n
 extended and justified in a fractional setting. A Monte Carlo study of\nfi
 nite-sample performance\, and a small empirical illustration\, are reporte
 d.\n
LOCATION:MR12
END:VEVENT
END:VCALENDAR