Forecasting maternal mortality rate in Malaysia

Maternal mortality remained a significant issue in Malaysia despite the advancements in healthcare. A key factor affecting maternal mortality rates is the decline in the number of pregnancies and live births. As Malaysia faces economic challenges such as rising living costs, stagnant wages, and financial instability, more women are choosing to delay or avoid pregnancy altogether. The primary objective of this study is to examine the pattern of maternal mortality in Malaysia from the year 1946 to 2023 and to estimate the maternal mortality rates for the next three years in Malaysia using Box-Jenkins methodology. The findings of this study showed that the pattern of maternal mortality rates in Malaysia from 1946 to 2023 was seen to be exponentially decaying. The data was divided into training and test sets for ARIMA analysis to assess the accuracy of the model. The Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) were used to evaluate the data’s stationarity to identify the model. Several ARIMA models were proposed, including ARIMA (1,1,1), ARIMA (1,1,2), ARIMA (2,1,1) and ARIMA (2,1,2). Based on its capacity to produce white noise errors, its effectiveness in fitting the data, and its precision in producing a precise forecast, the ARIMA (1,1,1) model was determined to be the best model. ARIMA (1,1,1) was determined to be the best model for forecasting maternal death rates in Malaysia based on the forecast accuracy and how well the model’s prediction matched the actual data. Maternal mortality rates were estimated to be 20.2, 24.6 and 21.1 in 2024, 2025 and 2026 respectively. Reducing maternal mortality requires better healthcare access, training, and public awareness. Future research should explore advanced models and higher-frequency data for improved accuracy.