Abstract

The data on maternal anaemia is highly skewed in sub-Saharan Africa, with some women showing higher and others lower levels of Haemoglobin (Hb). A thorough analysis of maternal anaemia data is crucial for identifying effective strategies, but success depends on the choice of model and its ability to handle outliers. The study evaluated mean, quantile, and robust regression methods, along with diagnostic statistics, on maternal Hb data in Malawi. The analysis used simulations and real Hb data from the 2015-16 Malawi Demographic and Health Survey, calculated with STATA version 17. The simulation results revealed that in large sample sizes, outlier detection rates were similar across linear, quantile, and robust regression models. Further, all models showed similar accuracy without outliers. For datasets with outliers, robust and quantile regression (1st and 2nd quartiles) provided the most accurate estimates with smaller biases compared to linear and higher percentile models. The real data analysis showed that directions of estimates were similar across the models, but the linear, robust M- and MM-estimator models produced estimates with smallest standard errors. The estimated average Hb level for women was 13.7 g/dl. Residing in rural area, higher body mass index, having primary and secondary education were linked to high Hb levels. While older pregnancy, drinking from safe water sources, and living in a rich household were associated with low Hb levels. The model residuals detected considerable amount of outliers in the data, mostly they were women with extremely low Hb levels. Diverse statistical methods can strengthen evidence of maternal anaemia in sub-Saharan Africa, supporting the determination of effective interventions. Policymakers in Malawi should develop strategies to increase Hb levels in pregnant women, especially in their second and third trimesters, and other marginalized groups.

More details

School	: School of Natural and Applied Sciences
Issued Date	: 2021

Download full document