BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//une sortie//unesortie.fr//FR
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:4b2d89fc-52c2-455b-aab9-72ab7f5d1719@unesortie.fr
DTSTAMP:20261101T041514Z
SUMMARY:[Séminaire Caen] Linear Regressions with Combined Data
DTSTART:20261109T131500Z
DTEND:20261109T144500Z
LOCATION:UFR SEGGAT - MRSH · Université de Caen Normandie\, 14000 Caen
DESCRIPTION:Abstract: We study linear regressions in a context where the ou
 tcome of interest and some of the covariates are observed in two different
  datasets that cannot be matched. Traditional approaches obtain point iden
 tification by relying\, often implicitly\, on exclusion restrictions. We s
 how that without such restrictions\, coefficients of interest can still be
  partially identified\, with the sharp bounds taking a simple form. We obt
 ain tighter bounds when variables observed in both datasets\, but not in
 …\n\nhttps://unesortie.fr/e/seminaire-caen-linear-regressions-with-combi
 ned-data-4b2d89/
URL:https://unesortie.fr/e/seminaire-caen-linear-regressions-with-combined-
 data-4b2d89/
END:VEVENT
END:VCALENDAR