BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Regression with Dependent Functional Errors-in-Pre
dictors - Xinghao Qiao (London School of Economics
)
DTSTART;TZID=Europe/London:20180517T110000
DTEND;TZID=Europe/London:20180517T120000
UID:TALK105733AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/105733
DESCRIPTION:Functional regression is an important topic in fun
ctional data analysis. Traditionally\, in function
al regression\, one often assumes that samples of
the functional predictor are independent realizati
ons of an underlying stochastic process\, and are
observed over a grid of points contaminated by ind
ependent and identically distributed measurement e
rrors. However\, in practice\, the dynamic depende
nce across different curves may exist and the para
metric assumption on the measurement error covaria
nce structure could be unrealistic. In this paper\
, we consider functional linear regression with se
rially dependent functional predictors\, when the
contamination of predictors by measurement error i
s "genuinely functional" with fully nonparametric
covariance structure. Inspired by the fact that th
e autocovariance operator of the observed function
al predictor automatically filters out the impact
from the unobservable measurement error\, we propo
se a novel generalized-method-of-moments estimator
of the slope function. The asymptotic properties
of the resulting estimators under different scenar
ios are established. We also demonstrate that the
proposed method significantly outperforms possible
competitors through intensive simulation studies.
Finally\, the proposed method is applied to a pub
lic financial dataset\, revealing some interesting
findings. This is a joint work with Cheng Chen an
d Shaojun Guo.
LOCATION:Seminar Room 2\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR