Bayesian-Negative Binomial Regression on Underreported Counts of Indonesian Female Trafficking Cases in 2023 using MCMC

The five-year report of the Task Force for the Prevention and Handling of Human Trafficking shows that in Indonesia from 2015 to 2019, 87.58% of human trafficking victims were women. Data of human trafficking cases often suffer from underreporting counts, where the number of reported incidents is smaller than the actual number of incidents. This study aims to estimate the actual number of cases of Indonesian female trafficking in 2023 using negative binomial regression underreported counts. Parameter estimation is conducted using a Bayesian approach through the Markov Chain Monte Carlo (MCMC) method with Gibbs sampling algorithm with a total of 5000 iterations and a burn-in period after 3000 iterations. This study utilizes secondary data sourced from Central Java Data Portal and Central Bureau of Statistics Indonesia, with the dependent variable is the reported number of Indonesian female trafficking in 2023 (Y) and three independent variables that are factors influencing female trafficking: the percentage of the poor population ( ), the open unemployment rate ( ), and the level of high school or equivalent education completion ( ). The estimated actual number of female trafficking cases in 2023 in Aceh and West Sumatra is 4 and 2 cases respectively, with the unreported number of female trafficking cases amounting to 2 cases each. The average of actual number of Indonesian female trafficking in 2023 is 9 cases, while the average of unreported number of Indonesian female trafficking in 2023 is 2 cases