BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A semiparametric model for heterogeneous panel data with fixed eff
 ects - Oliver Linton\, Department of Economics\, University of Cambridge
DTSTART:20121102T160000Z
DTEND:20121102T170000Z
UID:TALK40838@talks.cam.ac.uk
CONTACT:Richard Samworth
DESCRIPTION:This paper develops methodology for semiparametric panel data\
 nmodels in a setting where both the time series and the cross section are\
 nlarge. Such settings are common in finance and other areas. We allow for\
 nheterogeneous nonparametric covariate effects as well as unobserved time 
 and\nfirm specific fixed effects that may depend on the covariates in an\n
 arbitrary way. We use a fixed effect transformation to eliminate the\nnuis
 ance parameters and then estimate the heterogeneous covariate effects\nusi
 ng time series nonparametric regressions. We propose a dimensionality\nred
 ucing common component structure that allows us to model the covariate\nef
 fect parsimoniously. We obtain the asymptotic theory of our proposed\nproc
 edures. We apply our methodology to a specific application\, that has\nbee
 n the subject of recent policy interest\, that is\, the effect of trading\
 nvenue fragmentation on market quality\, such as liquidity and volatility.
  We\nuse a unique dataset that reports at the weekly frequency since 2008 
 the\nlocation and volume of trading on the FTSE350 companies until 2011. W
 e find\nthat the effect of competition\, as measured by the Herfindahl ind
 ex of\nconcentration\, on market quality is nonlinear and non monotonic. T
 he implied\nquality of the market under perfect competition is superior to
  that under\nmonopoly provision\, but the transition between the two is co
 mplicated.
LOCATION:MR12\, CMS\, Wilberforce Road\, Cambridge\, CB3 0WB
END:VEVENT
END:VCALENDAR