The sex ratio at birth (SRB; defined as the ratio of male to female births) in Vietnam has been reported imbalanced since the 2000s. Previous studies have shown variations in the SRB across geographic locations based on survey and census data. Given the lack of reliable administration data on birth in Vietnam, it is crucial to model the levels and trends in the SRB based on a reproducible statistical approach. We use a Bayesian hierarchical time series model to estimate and project SRB in Vietnam by region from 1980 to 2050. The true level of the SRB in a Vietnam region in a certain year is modeled as the sum of two parts. Part 1 captures the baseline SRB value and the year-by-year natrual fluctuation. The natural fluctuation is modeled with an AR(1) time series model on log scale. Part 2 captures the unnatural imbalanced levels of SRB. The parameters related to the SRB imbalance follows normal hierarchical distributions to allow information exchange across Vietnam regions. Model results show that the northern Vietnam is estimated to have the most sever SRB imbalance among all regions, and this trend is projected to continue after 2020.
Contributed Papers - Time Series Modeling.