Small Area Estimation of Age-Specific and Total Fertility Rates in Bangladesh

Abstract Bangladesh has experienced a rapid national decline in fertility recent decades, however, rates vary considerably at the sub-national level (i.e., division). These variations are expected to be more pronounced lower levels of geography (e.g., district level). However, routinely conducted demographic health surveys designed for estimates and do not have adequate samples produce reliable estimate administrative units, particular when considering age-specific rates. Data extracted from Demographic Health Survey 2014 used derive direct associated smoothed standard errors. as inputs developing small area model, which is expressed hierarchical Bayesian framework fitted by Markov Chain Monte Carlo simulation. The model accounts variation different levels—women age-group, division, district. modeling results show large reductions estimated standards errors provide consistent detailed level. There significant differences within between districts division Fertility observed higher Sylhet women aged 20–24 years. We use geo-spatial maps visualize over districts, identify hot cold-spots better targeted local planning policy decision making further Bangladesh.