Multiple Systems Estimation for Sparse Capture Data: Inferential Challenges when there are Non-Overlapping Lists
share
Multiple systems estimation strategies have recently been applied to quantify hard-to-reach populations, particularly when estimating the number of victims of human trafficking and modern slavery. In such contexts, it is not uncommon to see sparse or even no overlap between some of the lists on which the estimates are based. These create difficulties in model fitting and selection, and we develop inference procedures to address these challenges. The approach is based on Poisson log-linear regression modeling and maximum likelihood inference of the parameters. The method routinely checks for the identifiability of a candidate model and existence of the corresponding maximum likelihood estimates. A stepwise method for choosing the most suitable parameters is developed. We apply the strategy to two empirical data sets of trafficking in US regions, and find that the approach results in stable, reasonable estimates. An accompanying R software implementation has been made publicly available.
READ FULL TEXT