Montag, 09. April 2018, 16:45 - 17:45 iCal

ISOR Colloquium

"Bounds on Treatment Effects in Regression Discontinuity Designs with a Manipulated Running Variable"

Speaker: Christoph Rothe (Univ. Mannheim)

HS 7 OMP1 (#1.303), 1st floor
Oskar-Morgenstern-Platz 1, 1090 Wien

Vortrag


The key assumption in regression discontinuity analysis is that the distribution ofpotential outcomes varies smoothly with the running variable around the cutoff. Inmany empirical contexts, however, this assumption is not credible; and the runningvariable is said to be manipulated in this case. In this paper, we show that while causaleffects are not point identified under manipulation, they remain partially identifiedunder a general model that covers a wide range of empirical patterns. We derive sharpbounds on causal parameters for both sharp and fuzzy designs under our general model,and show how additional structure can be used to further narrow the bounds. We useour methods to study the disincentive effect of unemployment insurance on (formal)reemployment in Brazil, and show that our bounds remain informative, despite the factthat manipulation has a sizable effect on our estimates of causal parameters.

Zur Webseite der Veranstaltung


Veranstalter

Institut für Statistik und Operations Research


Kontakt

Mag. Vera Lehmwald
Fakultät für Wirtschaftswissenschaften
Institut für Statistik und Operations Research
+43 1 4277 38651
vera.lehmwald@univie.ac.at