 |
Test Design Under Falsification
Abstract : We characterize a receiver-optimal test when manipulations are possible in the form of type falsification. Optimal design exploits the following manipulator trade-off: while falsification may lead to better grades, it devalues their meaning. We show that optimal tests can be derived among falsification-proof ones. Our optimal test has a single ‘failing’ grade, and a continuum of ‘passing’ grades. It makes the manipulator indifferent across all moderate levels of falsification. Good types never fail, but bad types may pass. An optimal test delivers at least half of the full-information value to the receiver. A three-grade optimal test also performs well.
https://hal-sciencespo.archives-ouvertes.fr/hal-03393136
Contributor : Spire Sciences Po Institutional Repository Connect in order to contact the contributor
Submitted on : Thursday, October 21, 2021 - 9:39:20 PM
Last modification on : Monday, March 21, 2022 - 2:47:48 PM
Long-term archiving on: : Saturday, January 22, 2022 - 9:17:03 PM
Contributor : Spire Sciences Po Institutional Repository Connect in order to contact the contributor
Submitted on : Thursday, October 21, 2021 - 9:39:20 PM
Last modification on : Monday, March 21, 2022 - 2:47:48 PM
Long-term archiving on: : Saturday, January 22, 2022 - 9:17:03 PM
File
2018-perez-and-skreta-test-des...
Publisher files allowed on an open archive
Licence
Distributed under a Creative Commons Attribution - NoDerivatives 4.0 International License