Modeling the Number of Maternal Deaths in East Java Province Using MM-Estimation and GM-Estimation Robust Regression

Maternal Mortality Rate (MMR) is one of the targets of the Sustainable Development Goals (SDGs), and MMR is set to be less than 70 per 100,000 live births by 2030. The MMR in Indonesia in 1991-2020 decreased from 390 to 189 per 100,000 live births. The reduction in MMR is still far from the target set by the SDGs. In 2022, the number of maternal deaths in Indonesia was 3,572, with East Java Province as a large contributor of 486 deaths. The aims of the research are the number of maternal deaths ( , the number of mothers experiencing hypertension ( , the number of mothers experiencing bleeding ( , the number of mothers experiencing infections ( , and the number of specialized hospitals ( . The methods used in this research are MM-Estimation and GM-Estimation robust regression. Robust regression was used because the data has outliers, so the residuals are not normally distributed. The results showed that the MM-Estimation and GM-Estimation model has an Adjusted R-squared value of 85.98% and 91.88% and AIC value of 201.1614 and 183.4612, with all independent variables significantly affecting maternal mortality. Based on the analysis, it is concluded that the robust regression GM-Estimation model is better than the MM-Estimation model because it has a larger Adjusted R-squared value and a smaller AIC value. The robust regression GM-Estimation model has the following equation: =1.893021+1.331650 +1.653501 +2.099621 -1.139574 .