Time Series Modeling of Livebirths and Stillbirths: A Case Study of Obafemi Awolowo University Teaching Hospital Complex, Ile-Ife

Abstract

: Livebirths and stillbirths are key public health indicators, with significant social and economic consequences. This study applies time series modeling to the quarterly data of livebirths and stillbirths recorded at Obafemi Awolowo University Teaching Hospital Complex (OAUTHC), Ile-Ife, spanning from 2001 to 2020. Using Augmented Dickey-Fuller tests, the data were confirmed to be stationary. Appropriate ARMA models ARMA(2,3) for livebirths and ARMA(1,3) for stillbirths were fitted based on minimum values of AIC, BIC, and HQIC. Forecasts show that livebirths are expected to fluctuate before stabilizing, while stillbirths are projected to remain relatively constants at around 30 cases per quarter. though with wide confidence intervals early in the forecast. However, the relatively low R2 values, especially for stillbirths, suggest that other unmeasured factors such as healthcare access, socio-economic conditions, or maternal risk factors may be influential. These findings underscore the importance of continuous improvement in maternal healthcare, data-driven planning and timely intervention.