Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/149763 
Year of Publication: 
2016
Series/Report no.: 
cemmap working paper No. CWP17/16
Publisher: 
Centre for Microdata Methods and Practice (cemmap), London
Abstract: 
This paper considers identification of treatment effects on conditional transition probabilities. We show that even under random assignment only the instantaneous average treatment effect is point identified. Because treated and control units drop out at different rates, randomization only ensures the comparability of treatment and controls at the time of randomization, so that long run average treatment effects are not point identified. Instead we derive informative bounds on these average treatment effects. Our bounds do not impose (semi)parametric restrictions, as e.g. proportional hazards. We also explore various assumptions such as monotone treatment response, common shocks and positively correlated outcomes that tighten the bounds.
Subjects: 
Partial identification
duration model
randomized experiment
treatment effect
JEL: 
C14
C41
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size
516.19 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.