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
Marco Ottaviani, IGIER Print
Tuesday, 20 December 2016, 14:00 - 15:15

Marco Ottaviani, IGIER

Strategic Sample Selection

Abstract: An evaluator tests an empirical hypothesis based on evidence provided by a researcher who is biased toward acceptance. The researcher constructs the sample by first collecting a pre-sample and then strategically selecting data for the sample. Selected data are not Blackwell comparable to random data. Building on and generalizing Lehmann’s classical result on the comparison of location experiments, the paper develops tools to characterize the impact of strategic sample selection on the payoff of evaluator and researcher.

The evaluator’s payoff is increasing/decreasing in the amount of manipulation when the distribution of the data has a quantile density (a.k.a. Tukey’s sparsity) function that is less/more elastic than Gumbel’s extreme value distribution. More generally, the evaluator is hurt when either the data distribution has sufficiently thick tails and the hypothesis would strongly be rejected at the prior, or the data distribution has sufficiently thin tails and the hypothesis would strongly be accepted at the prior.

When the data follows the Gumbel distribution, the evaluator is always unaffected by strategic sample selection; in that case data manipulation is a pure rat race and results in a loss for the researcher equal to the cost of all the extra data collected.


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