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. 

Is self-defense just one of those issues where we'll never have decent
data? Fabio 

On Wed, 5 Feb 2003, William Dickens wrote:
> Which is highly suspect. It is computed by projecting the fraction of
> people in a relatively small sample who say they used firearms
> defensively to the whole population. Anyone who has ever worked with
> survey data knows that error rates of a couple of percent (at least)
> on all sorts of questions are common. Both coding errors and reporting
> errors substantially increase (in percentage terms) the fraction of
> respondents giving positive responses to questions with very low
> fractions of positive responses. Think also about how people treat
> surveys (for example the number of people who say they have been
> abducted by aliens).  I would bet any money that the true fraction of
> people who use firearms in self-defense (brandishment or otherwise) is
> a whole heck of a lot lower (an order of magnitude or more) than what
> is suggested by Kleck's survey. - - Bill Dickens
> William T. Dickens

Reply via email to