How would one estimate the accuracy of self-reports of self-defense? I
know in medical research you can assess the validity of self-reported
health by doing follow up medical exams or seeing if the respondent dies
or becomes seriously ill shortly after the survey.
One possibility would be to check for consistency with other measures.

Suppose, for example, one had a poll of criminals, taken in some situation where they had no reason to lie. Every case of a victim frightening a way a criminal by brandishing a gun at him ought in principle to show up on both sides of the transaction.

For an analogous case, one can check poll results on sexual activity by heterosexuals by comparing what men say with what women say.
David Friedman
Professor of Law
Santa Clara University

Reply via email to