Henry Farrell applies the list experiment technique (see here or here) to investigate the prevalence of voter fraud:
One of the findings of a new working paper by John Ahlquist, Kenneth R. Mayer and Simon Jackman is that “the lower bound on the population reporting voter impersonation is nearly identical with the proportion of the population reporting abduction by extraterrestrials.” Roughly 2.5 percent of the population effectively admit to one or the other. The rationale for this comparison tells us a lot about how social scientists deal with complex and touchy political issues.
They conclude:
The implication here is that if one accepts that 2.5% is a valid lower bound for the prevalence of voter impersonation in the 2012 election then one must also accept that about 2.5% of the adult U.S. population – about 6 million people – believe that they were abducted by extra-terrestrials in the last year. If this were true then voter impersonation would be the least of our worries.
Information Knoll 