Eliciting Illegal migration rates through list randomization
David McKenzie & Melissa Siegel
#2013-023
Most migration surveys do not ask about the legal status of migrants due
to concerns about the sensitivity of this question. List randomization
is a technique that has been used in a number of other social science
applications to elicit sensitive information. We trial this technique by
adding it to surveys conducted in Ethiopia, Mexico, Morocco and the
Philippines. We show how, in principle, this can be used to both give an
estimate of the overall rate of illegal migration in the population
being surveyed, as well as to determine illegal migration rates for
subgroups such as more or less educated households. Our results suggest
that there is some indication in this method: we find higher rates of
illegal migration in countries where illegal migration is thought to be
more prevalent and households who say they have a migrant are more
likely to report having an illegal migrant. Nevertheless, some of our
other findings also suggest some possible inconsistencies or noise in
the conclusions obtained using this method, so we suggest directions for
future attempts to implement this approach in migration surveys.
Keywords: Illegal migration; List Randomization; Item Count Method;
Survey Techniques
JEL codes: F22, C83, J61, K42