College of Science

Permanent URI for this collection

https://ir.knust.edu.gh/handle/123456789/15

Browse

Browsing College of Science by Subject "ARIMA"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Analysis of Maternal Mortality with Time; a Case Study of the Okomfo Anokye Teaching Hospital – Kumasi (2000-2010)
    (2012) Asomaning, Sarpong Smart
    This study examined the occurrence and incidence of Maternal Deaths as well as maternal mortality ratios at the Okomfo Anokye Teaching Hospital in Kumasi from 2000 to 2010. The study explored the feasibility for application of Poisson models and time series autoregressive integrated moving average (ARIMA) in the study of occurrence and incidence of Maternal Deaths and to predict Maternal Mortality ratios respectively. Analyses were based on data available at the Bio-Statistics Department of the Obstetrics & Gynaecology directorate of the Okomfo Anokye Teaching Hospital in Kumasi for the period 2000-2010. The Statistical Analysis software (SAS) as well as the R-consol statistical analysis software was used in analysing the data. We found that, the mean number of occurrence of maternal death cases were high for all the years considered and established that the mean number of occurrence of maternal death cases has not significantly reduced over the period 2000 to 2010. The result also shows that there was a statistically significant in the incidence of maternal deaths difference between year 2010 (the referenced year) and years 2004, 2005 and 2008. Their chi-square values were 3.95, 5.12 and 5.83 with p-values of 0.0469, 0.0236 and 0.0158 respectively. Finally, the hospitals Maternal Mortality Ratio (MMR) is relatively stable but has a very high average MMR of 967.7 per 100,000 live births which is about twice the National ratio of 451 per 100,000 live births. An ARIMA model fitted was used to predict maternal mortality ratios (MMRs) for the next eight quarters. We conclude that statistically the mean rate of maternal death cases is not significant over the period of time under study, mean number of occurrence of maternal death cases has not significantly reduced over the period 2000 to 2010 and that the ARIMA model is adequate for forecasting quarterly maternal mortality ratios at the hospital.