Menu Content/Inhalt
Seminars Print
previous year previous month next month next year
See by year See by month See by week See Today Search Jump to month
Denni Tommasi, ECARES Print
Friday, 02 December 2016, 12:15 - 13:15

Denni Tommasi,  ECARES

LATE With Mismeasured or Misspecified Treatment

Abstract : We show that a local average treatment effect (LATE) can be identified and consistently estimated even when the treatment indicator might be mismeasured, or is estimated using a possibly misspecified structural model. This is a common situation in economics, where relevant treatments can concern, e.g., expectations, ability, opportunity, or utility. In our empirical application, treatment is a measure of empowerment, specifically, whether a wife has control of the majority of her household's resources. Due to both measurement errors in expenditures and sharing of public goods within a household, this treatment cannot be directly observed without error, and so must be estimated. Our outcomes are the health status of family members, using data from India. We first estimate a structural model to obtain the otherwise unobserved treatment indicator. Then, using changes in Indian inheritance laws as a plausibly unconfounded instrument, we apply our new estimator of LATE. Our estimator accounts for possible measurement, estimation, and specification errors in the estimated treatment indicator. We find that women's empowerment substantially decreases their probability of being anemic or underweight, and increases children's likelihood of receiving vaccinations.

Location: R42.2.113
Contact: Nancy De Munck, This e-mail address is being protected from spam bots, you need JavaScript enabled to view it