Synthetic control method: Difference between revisions

Revision as of 02:25, 10 August 2016

Revision as of 14:53, 27 April 2017

Line 13:

yields an estimator of <math>\alpha_{1t}</math> in periods <math>T_0+1,T_0+2,...,T</math>

The W* was solved by minimizeminimizing:

<math> \left\| \mathbf{X_1-X_0W} \right\|_V = \sqrt{(X_1-X_0W)'V(X_1-X_0W)}</math>, where ''''V'''' is defined as (k×k) symmetric and positive semidefinite matrix. V* is chosen among all positive definite and diagnal matrices such that the mean square prediction error (MSPE) of the outcome variable is minimized over the pre-intervention period.