RT Generic
T1 dqd: A command for treatment effect estimation under alternative assumptions
A1 Mora, Ricardo
A1 Reggio, Iliana
A2 Universidad Carlos III de Madrid. Departamento de Economía, 
AB Conventional difference-in-differences (DID) methods that are used to estimate the effect of atreatment rely on important identifying assumptions. Identification of the treatment effect in aDID framework requires some assumption relating trends for controls and treated in absence oftreatment, the most common being the assumption of Parallel Paths. When several pre-treatmentperiods are available, Mora and Reggio (2012) show that treatment effect identification does notuniquely depend on the Parallel Path assumption, but also on the trend modeling strategy. Theyfurther define a family of alternative Parallel assumptions and propose a more flexible modelwhich can be a helpful starting tool to study robustness to alternative Parallel assumptions andtrend dynamics. In this paper we introduce a Stata command that implements the fully flexiblemodel presented in Mora and Reggio (2012), producing tests for the equivalence of alternativeparallel assumptions and for the dynamic effects of the treatment. The standard DID in modelwith or without polynomial trends can also be obtained.
SN 2340-5031
YR 2014
FD 2014-04-01
LK https://hdl.handle.net/10016/18857
UL https://hdl.handle.net/10016/18857
LA eng
NO We acknowledge financial help from the Spanish government through grant ECO2012-31358.
DS e-Archivo
RD 13 may. 2024