BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260605T171618EDT-4458Ma1AJm@132.216.98.100
DTSTAMP:20260605T211618Z
DESCRIPTION:Efficient estimation in sub and full populations with monotonic
 ally missing at random data.\n\nWe consider estimation of a parameter defi
 ned by moment restrictions on a target population charac- terized by the m
 issingness pattern of monotonically missing at random data. Attrition or d
 ropout in a\, say\, R-period study/survey typically generates such data. I
 n this case\, a generic target is the underlying population of the sample 
 units dropping out in contiguous periods a\, . . . \, b where a <= b in {1
 \, . . . \, R}. The semiparametric efficiency bound and the efficient infl
 uence function are obtained for the parameter of interest from the generic
  target nesting the well-known special cases with (a = 1\, b = R) or (R = 
 2\, a = b = 1). Our results\, however\, differ fundamentally from the exis
 ting literature in that the consideration of a generic target beyond those
  special cases provides new insights on the usability and contribution of 
 the sam- ple units toward efficient estimation. Efficient estimation turns
  out to be standard MINPIN estimation with asymptotic properties directly 
 following from the well-known existing results. Further desirable properti
 es follow since the concerned MINPIN estimating functions are also doubly 
 robust to parametric misspecifica- tion of the nonparametric nuisance comp
 onents. A Monte Carlo study demonstrates all these nice properties of the 
 efficient estimator and the t-test based on it. A simple empirical illustr
 ation using the Project STAR data demonstrates substantive improvement in 
 precision over the standard but inefficient estimators.We consider estimat
 ion of a parameter defined by moment restrictions on a target population c
 harac- terized by the missingness pattern of monotonically missing at rand
 om data. Attrition or dropout in a\, say\, R-period study/survey typically
  generates such data. In this case\, a generic target is the underlying po
 pulation of the sample units dropping out in contiguous periods a\, . . . 
 \, b where a <= b in {1\, . . . \, R}. The semiparametric efficiency bound
  and the efficient influence function are obtained for the parameter of in
 terest from the generic target nesting the well-known special cases with (
 a = 1\, b = R) or (R = 2\, a = b = 1). Our results\, however\, differ fund
 amentally from the existing literature in that the consideration of a gene
 ric target beyond those special cases provides new insights on the usabili
 ty and contribution of the sam- ple units toward efficient estimation. Eff
 icient estimation turns out to be standard MINPIN estimation with asymptot
 ic properties directly following from the well-known existing results. Fur
 ther desirable properties follow since the concerned MINPIN estimating fun
 ctions are also doubly robust to parametric misspecifica- tion of the nonp
 arametric nuisance components. A Monte Carlo study demonstrates all these 
 nice properties of the efficient estimator and the t-test based on it. A s
 imple empirical illustration using the Project STAR data demonstrates subs
 tantive improvement in precision over the standard but inefficient estimat
 ors.\n
DTSTART:20180321T193000Z
DTEND:20180321T203000Z
LOCATION:Room D-4\, CA\, QC\, J1K 2R1\, Université de Sherbrooke\, 2500 Bou
 l. de l'Université
SUMMARY:Saraswata Chaudhuri\, Department of Economics\, 91ºÚÁÏÍø
URL:/mathstat/channels/event/saraswata-chaudhuri-depar
 tment-economics-mcgill-university-285892
END:VEVENT
END:VCALENDAR