Anytime-valid inference for synthetic control

PhD Seminar

We study online inference for synthetic control, which is valid even if we test after every new post-treatment observation. Specifically, we introduce three tests that are ‘anytime-valid’ under different assumptions on the DGP and the treatment allocation mechanism. 

Speaker
Date
Wednesday 15 May 2024, 13:00 - 14:00
Type
Seminar
Room
4.12
Add to calendar

While our theoretical results rely on strong exchangeability assumptions for exact validity, Monte Carlo simulations suggest the methods work well in more realistic settings. 

We provide an empirical example through an analysis of the California Tobacco Control programme.

See also

Correcting Beliefs about the Marginal Tax Rate: A Survey Experiment among Dutch Households

Arjan Non (Erasmus School of Economics)
Image - Dutch Town
Image - Schoolkids

A Tale of Two Markups: Reconciling Supply- and Demand-Based Estimates

Luca Dedola (ECB)

Policy Afternoon 'Shortages in the Labour Market'

With a keynote by Prof. Rafael Lalive, followed by a round table discussion
Students and staff sit outside in the sun at Erasmus Pavilion.

Compare @count study programme

  • @title

    • Duration: @duration
Compare study programmes