Time and Causality: A Monte Carlo Assessment of the Timing-of-Events Approach
Link to article:
Authors:
Gaure, Simen, Knut Røed and Tao Zhang
Year:
2007
Reference:
Vol 141, 1159-1195Nummer i serie: 141Summary
We present new Monte Carlo evidence regarding the feasibility of separating causal-ity from selection within non-experimental duration data, by means of the nonpara-metric maximum likelihood estimator (NPMLE). Key findings are: i) the NPMLE is extremely reliable, and it accurately separates the causal effects of treatment and dura-tion dependence from sorting effects, almost regardless of the true unobserved hetero-geneity distribution; ii) the NPMLE is normally distributed, and standard errors can be computed directly from the optimally selected model; and iii) unjustified restric-tions on the heterogeneity distribution, e.g., in terms of a pre-specified number of support points, may cause substantial bias.
JEL:
C14, C15, C41,
Keywords:
NPMLE, treatment effect
Project:
Oppdragsgiver: Norges forskningsrådOppdragsgivers prosjektnr.:
Frisch prosjekt: 1151 - Mobilizing labour force participation
Financing:
Norges Forskningsråd