Small Area Estimation of Child Trafficking Proportions in Chiefdoms of Sierra Leone and Overall Ranking of the Chiefdoms

Music City Center 

Human trafficking and child trafficking wreak gravely critical human rights violation. Child trafficking is a despicable form of crime inflicted upon the most vulnerable segment of the society. Reliable estimates of prevalences of child trafficking for various subpopulations is the first priority in tackling this problem. In our study, subpopulations are children aged 5-17 living in small geographic regions (or chiefdoms) in Sierra Leone. We develop improved estimates of the true rates of prevalence and identify the most adversely affected regions by estimating the unknown true ranks. These estimates shed light on the severity of the problem and bring attention to the critically affected regions (that is, chiefdoms). Using household survey data from Sierra Leone we propose a unit-level hierarchical Bayes probit regression model to reliably estimate the prevalence rates of trafficking in the chiefdoms. Using Markov chain Monte Carlo generated samples of the small area characteristics from the posterior distribution of the hierarchical Bayes model, we compute point and interval estimates of the prevalence rates, and a set of probability distributions for the unknown true ranks of the small areas in terms of their prevalence rates.

Credible distributions

Credible intervals

Data augmentation

Gibbs sampling

Hierarchical Bayes

Probit regression