BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251109T132006EST-5932PskF5N@132.216.98.100
DTSTAMP:20251109T182006Z
DESCRIPTION:'Efficient estimation of regression models with user-specified 
 parametric model for heteroskedasticity'\n\nEric Renault\, Warwick Univers
 ity\n	November 1\, 2022\, 12:00 to 1:00 PM\n	Leacock 429\n\nAbstract:\n	Sever
 al modern textbooks report that\, thanks to the availability of heterosked
 asticity robust standard errors\, one observes the near-death of Weighted 
 Least Squares (WLS) in cross-sectional applied work. We argue in this pape
 r that it is actually possible to estimate regression parameters at least 
 as precisely as OLS and WLS\, even when using a misspecified parametric mo
 del for conditional heteroskedasticity. Our analysis is valid for a genera
 l regression framework (including Instrumental Variables and Nonlinear Reg
 ression) as long as the regression is defined by a conditional expectation
  condition. The key is to acknowledge\, as first pointed out by Cragg (199
 2) that\, when the user-specific heteroskedasticity model is misspecified\
 , WLS has to be modified depending on a choice of some univariate target f
 or estimation. Moreover\, targeted WLS can be improved by properly combini
 ng moment equations for OLS and WLS respectively. Efficient GMM must be re
 gularized to take into account the possible multicolinearity of estimating
  equations when errors terms are actually nearly homoscedastic.\n
DTSTART:20221101T160000Z
DTEND:20221101T170000Z
LOCATION:Room 429\, Leacock Building\, CA\, QC\, Montreal\, H3A 2T7\, 855 r
 ue Sherbrooke Ouest
SUMMARY:Eric Renault (Warwick University)\, 'Efficient estimation of regres
 sion models with user-specified parametric model for heteroskedasticity'
URL:/economics/channels/event/eric-renault-warwick-uni
 versity-efficient-estimation-regression-models-user-specified-parametric-3
 42975
END:VEVENT
END:VCALENDAR