BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250312T194744EDT-4282mgxvg8@132.216.98.100
DTSTAMP:20250312T234744Z
DESCRIPTION:Federico Bugni (Duke University)\n	Host: Saraswata Chaudhuri\n\n
 Date: February 28\, 2020\n	Location: Leacock 429\n\nWebsite: https://sites.
 duke.edu/federicobugni/\n\n'Testing Continuity of a Density via g-order st
 atistics in the Regression Discontinuity Design”\n\nAbstract:\n	In the regr
 ession discontinuity design (RDD)\, it is common practice to assess the cr
 edibility of the design by testing the continuity of the density of the ru
 nning variable at the cut-off\, e.g.\, McCrary (2008). In this paper we pr
 opose a new test for continuity of a density at a point based on the so-ca
 lled g-order statistics\, and study its properties under a novel asymptoti
 c framework. The asymptotic framework is intended to approximate a small s
 ample phenomenon: even though the total number n of observations may be la
 rge\, the number of effective observations local to the cut-off is often s
 mall. Thus\, while traditional asymptotics in RDD require a growing number
  of observations local to the cut-off as n grows\, our framework allows fo
 r the number q of observations local to the cut-off to be fixed as n grows
 . The new test is easy to implement\, asymptotically valid under weaker co
 nditions than those used by competing methods\, exhibits finite sample val
 idity under stronger conditions than those needed for its asymptotic valid
 ity\, and has favorable power properties against certain alternatives. In 
 a simulation study\, we find that the new test controls size remarkably we
 ll across designs. We finally apply our test to the design in Lee (2008)\,
  a well-known application of the RDD to study incumbency advantage.\n
DTSTART:20200228T203000Z
DTEND:20200228T220000Z
LOCATION:Leacock 429\, Leacock Building\, CA\, QC\, Montreal\, H3A 2T7\, 85
 5 rue Sherbrooke Ouest
SUMMARY:Federico Bugni (Duke University)\, 'Testing Continuity of a Density
  via g-order statistics in the Regression Discontinuity Design”
URL:/economics/channels/event/federico-bugni-duke-univ
 ersity-testing-continuity-density-g-order-statistics-regression-301117
END:VEVENT
END:VCALENDAR