Das Sumonkanti, Kumar Bappi, Kawsar Luthful Alahi
Department of Quantitative Economics, Maastricht University, Maastricht, The Netherlands.
Department of Statistics, Shahjalal University of Science & Technology, Sylhet, Bangladesh.
PLoS One. 2020 May 20;15(5):e0220164. doi: 10.1371/journal.pone.0220164. eCollection 2020.
Acute respiratory infection (ARI) and diarrhoea are two major causes of child morbidity and mortality in Bangladesh. National and regional level prevalence of ARI and diarrhoea are calculated from nationwide surveys; however, prevalence at micro-level administrative units (say, district and sub-district) is not possible due to lack of sufficient data at those levels. In such a case, small area estimation (SAE) methods can be applied by combining survey data with census data. Using an SAE method for the dichotomous response variable, this study aims to estimate the proportions of under-5 children experienced with ARI and diarrhoea separately as well as either ARI or diarrhoea within a period of two-week preceding the survey. The ARI and diarrhoea data extracted from Bangladesh Demographic and Health Survey 2011 are used to develop a random effect logistic model for each of the indicators, and then the prevalence is estimated adapting the World Bank SAE approach for the dichotomous response variable using a 5% sample of the Census 2011. The estimated prevalence of each indicator significantly varied by district and sub-district (1.4-11.3% for diarrhoea, 2.2-11.8% for ARI and 4.3-16.5% for ARI/diarrhoea at sub-district level). In many sub-districts, the proportions are found double of the national level. District and sub-district levels spatial distributions of the indicators might help the policymakers to identify the vulnerable disaggregated and remote hotspots. Particularly, aid industries can provide effective interventions at the highly vulnerable spots to overcome the gaps between micro and macro level administrative units.
急性呼吸道感染（ARI）和腹泻是孟加拉国儿童发病和死亡的两大主要原因。ARI和腹泻在国家和地区层面的患病率是通过全国性调查计算得出的；然而，由于微观行政单位（如区和分区）缺乏足够的数据，无法计算这些层面的患病率。在这种情况下，可以通过将调查数据与人口普查数据相结合来应用小区域估计（SAE）方法。本研究旨在使用SAE方法处理二分响应变量，估计调查前两周内5岁以下儿童分别患ARI和腹泻以及患ARI或腹泻的比例。从《2011年孟加拉国人口与健康调查》中提取的ARI和腹泻数据用于为每个指标建立随机效应逻辑模型，然后采用世界银行SAE方法，利用2011年人口普查5%的样本估计二分响应变量的患病率。各指标的估计患病率在区和分区层面存在显著差异（分区层面腹泻患病率为1.4 - 11.3%，ARI患病率为2.2 - 11.8%，ARI/腹泻患病率为4.3 - 16.5%）。在许多分区，这些比例是全国水平的两倍。各指标在区和分区层面的空间分布可能有助于政策制定者识别脆弱的细分区域和偏远热点地区。特别是，援助行业可以在高度脆弱的地区提供有效的干预措施，以弥合微观和宏观行政单位之间的差距。
