Abstract

We propose a method for analyzing repeated residential movements based on graphical loglinear models. This method allows an explicit representation of residential presence and absence patterns from several areas without defining mobility measures. We make use of our method to analyze data from one of the most comprehensive demographic surveillance sites in Africa that is characterized by high adult HIV prevalence, high levels of poverty and unemployment and frequent residential changes. Between 2004 and 2016, residential changes were recorded for 8,857 men over 35,500.01 person-years, and for 12,158 women over 57,945.35 person-years. These individuals were HIV negative at baseline. Over the study duration, there were a total of 806 HIV seroconversions in men, and 2,458 HIV seroconversions in women. Our method indicates that establishing a residence outside the rural study area is a strong predictor of HIV seroconversion in men (OR = 2.003, 95% CI = [1.718,2.332]), but not in women. Residing inside the rural study area in a single or in multiple locations is a less significant risk factor for HIV acquisition in both men and women compared to moving outside the rural study area.