Comparing the Forecasting Performance of Seasonal Arima and Holt -Winters Methods of Births at a Tertiary Healthcare Facility in Ghana (original) (raw)
Related papers
Journal of Biology Agriculture and Healthcare, 2014
The use of maternal healthcare facilities is an important indicator of the impact of the free maternal healthcare policy aimed at improving health status of pregnant women in Ghana. This study investigated the pattern of quarterly assisted deliveries at Komfo Anokye Teaching Hospital (KATH), Kumasi, Ghana from 2000 to 2011. The Holt Winters multiplicative and additive forecasting models were considered. The Multiplicative model reported a Root Mean Square Error of Prediction (RMSEP) of 31.10, Root Mean Square Error (RMSE) of 188.080, Mean Absolute Percentage Error (MAPE) of 6.2951 and Mean Absolute Scaled Error (MASE) of 0.7086 while the additive model reported RMSEP, RMSE, MAPE and MASE of 49.59 201.83, 6.3098 and 0.7106 respectively .The multiplicative model further passed the Shapiro-Wilks test (p-value 0.07358). Results identified the second and fourth quarters as peak seasons and the first quarters as deep seasons for assisted childbirths in the hospital. The negative binomial regression confirmed this by identifying April, May, October and November as peaks months with May being the most significant month.
Modeling and Forecasting Maternal Mortality; an Application of ARIMA Models
International Journal of Applied, 2013
This study examines maternal mortality ratios at the Okomfo Anokye Teaching Hospital in Kumasi from the year 2000 to 2010. The study explores the feasibility for application of Box-Jenkins Approach to time series autoregressive integrated moving average (ARIMA) in modeling and forecasting Maternal Mortality ratios (MMR). Analyses were based on data available at the Bio-Statistics Department of the Obstetrics& Gynaecology directorate of the facility. The result shows that the hospitals Maternal Mortality Ratio (MMR) was relatively stable but had a very alarmingaverage quarterlyMMR of 967.7 per 100,000 live births which is about twice the National ratio of 451 per 100,000 live births. With AIC (581.41), we conclude that the ARIMA (1,0,2) model is adequate for forecasting quarterly maternal mortality ratios at the hospital.
Autoregressive Integrated Moving Average (ARIMA) Models for Birth Forecasting
Journal of the American Statistical Association, 1977
Analysis of exchange rate using ARIMA model, was carried out to help those in charge of the economy who are carried out to help those in charge of the economy who are interested in the strange and irregular trend in the Nigerian exchange rate system, to identify the exchange rate model, estimate the model parameters and predict or forecast the future. In an effort to better understand how exchange rate can be modeled, this work applied ARIMA model to exchange rate (Naira to Dollar) within the periods 1982-2011, through Box-Jenkins methodology an AR(1): order one was generated model is preferred as it was proved through the diagnostic rate of Naira-Dollars based on its potentials for better prediction and computational requirements.
Modeling births at a tertiary health-care facility in Ghana: Box-Jenkins time series approach
2017
Background & Aim: Changes in the trend of births among women have been studied worldwide with indications of peaks and troughs over a specified period. Periodic variations in the number of births among women are unknown at the Korle-Bu Teaching Hospital (KBTH). This study sought to model and predicts monthly number of births at the Department of Obstetrics and Gynaecology (O&G), KBTH. Methods & Materials: Box-Jenkins time series model approach was applied to an 11-year data from the Department of (O&G), KBTH on the number of births from January, 2004 to December, 2014. Box-Jenkins approach was put forward as autoregressive integrated moving average (ARIMA) model. Several possible models were formulated, and the best model, which has the smallest Akaike information criterion corrected (AICc) was selected. The best model was then used for future predictions on the expected monthly number of births for the year 2015. Analysis was performed in R statistical software (version 3.0.3). Res...
TIME SERIES ANALYSIS AND FORECAST OF INFANT MORTALITY RATE IN NIGERIA: AN ARIMA MODELING APPROACH
Childhood mortality in general and infant mortality in particular has long been a public health menace in Nigeria. Identified as one of the barometers for the measurement of any population's state of health, health facilities and well being, relevant authorities in government and stakeholders in public health have all moved to reduce and possibly eliminate its occurrence with little success. This is evident in the fact that Nigeria was one of the countries that failed to meet the Millennium Development Goal (MDG) for the reduction of childhood mortality by two-thirds in 2015. Having failed to achieve MDG 4, genuine concerns of her ability to achieve the Sustainable Development Goal (SDG) 3.2 by 2030 has led to an inquest into the country's chances of reducing childhood mortality rate occurring within the first year of life. The present study utilized the Auto-Regressive Integrated Moving Average (ARIMA) model for to make forecast of infant mortality in Nigeria up to the year 2030 using data obtained from the United Nation's Inter Agency Group for Childhood Mortality Estimation (UN-IGME). The ARIMA (1, 1, 1) model selected predicted a reduction of up to 30% by 2030 at 95% confidence interval.
2018
This study present autoregressive integrated moving average (ARIMA) models to forecast monthly patient demand for Paediatric clinic at a private hospital in Kuantan. The ARIMA model developed hold potential for providing operational decision support in the hospital. The forecasting success attained for the Paediatric clinic could aid managers to make capacity and advance planning in the wards and hospital. The ARIMA model was developed from time series data routinely-collected at Paediatric clinic. The study evaluated patient demand at Paediatric clinic by using time series data collected from year 2012 until year 2017. Analyses of time series data of Paediatric clinic produce ARIMA (2, 0, 2) model of monthly data. The ARIMA (2, 0, 2) give rise to MAPE of 11.988 percent respectively, therefore ARIMA (2, 0, 2) model was selected for modelling and forecasting paediatric patient demand based on the lowest MAPE values. The out of sample forecast by using ARIMA (2, 0, 2) model indicated ...
Forecasting Monthly Maternal Mortality in the Bawku Municipality, Ghana Using SARIMA
Maternal mortality is defined as the death of a woman while pregnant or within 42 days of termination of pregnancy, irrespective of the duration and site of the pregnancy, from any cause related to or aggravated by the pregnancy or its management. Maternal mortality which accounts for 14% of all female deaths is still the second largest cause of female deaths in Ghana. Maternal mortality is very high in the northern regions of Ghana hence the need to model and forecast maternal mortality data to give insight to public health workers so as to combat any expected high maternal mortality. This study therefore models and also forecast future maternal mortality trends in the Bawku Municipality of the Upper East Region of Ghana using Box-Jenkins Approach. Analyses were based on monthly data available at the Biostatistics department of the municipal hospital. Results show that SARIMA (3, 0, 0) × (1, 1, 2) 12 adequately models the maternal mortality data. The forecasted values also revealed that, maternal mortality cases increased during the months of May to July and from September to December, which is an insight for public health workers.
Time Series Analysis and Forecasting of Caesarian Section Births in Ghana
Biomedical Statistics and Informatics, 2019
Caesarian Section (CS) rates have been known to have geographical varaitions. The purpose of this paper was to determine Ghana's situation (regional trend) and also to provide a two-year forcast estimates for the ten (10) regions of Ghana. The data was longitudinal and comprised monthly CS records of women from 2008 to 2017. The dataset was divided into training and testing dataset. A total of eighty four (84) months were used as the training dataset and the remaining thirty six (36) months were used as testing dataset. The ARIMA methodology was applied in the analysis. Augmented Dicker-Fuller (ADF), KPSS and the Philips-Perron (PP) unit root tests were employed to test for stationarity of the series plot. KPSS (which is known to give more robust results) and PP test consistently showed that the series was stationary (p ＜ 0.05) for all ten (10) regions, although there were some conflicting results with the ADF test for some regions. Tentative models were formulated for each region and the model with the lowest AIC was selected as the "Best" model fit for respective regions of Ghana. The "best" Model fit for Greater Accra, Central and Eastern regions were respectively SARIMA (2, 0, 0) (0, 1, 1) 12 , SARIMA (2, 0, 0) (0, 1, 1) 12 with a Drift and SARIMA (1, 1, 1) (0, 1, 1) 12. Additionally, the best model fit for Northern and Volta regions were SARIMA (3,0,2) (0,1,1) 12 with drift and SARIMA (0,1,1) (0,1,1) 12. Ashanti, Upper East and Western regions failed the JB test or the normality test for the residuals. Upper West and Brong Ahafo Regions were not suitable for forecasting due failure to depict white noise and ARCH test failure, respectively. The best models fit were used to forecast for 2019 and 2020. The results showed that regional variations of CS exist in Ghana. The study recommended for future studies to apply methods that will allow for forecasting for regions which failed the test under the methods used in this study.
Asian Journal of Probability and Statistics, 2022
Paper proposes an appropriate time series model that is used to forecast the NMR in Nigeria. The data used for the study is sourced from the World Bank for a period of 1980-2019. The ARIMA model and Exponential Smoothing are fitted on the raw data. The Bayesian Information Criterion (BIC) is adopted to assess the adequacy of the ARIMA models. The NMR series is stationary after the second differencing. The ARIMA (0,2,0) with BIC value of -3.358 is considered the appropriate model among other ARIMA models, and it is compared to SES and Brown’s LT using Theil’s U Statistics and MAPE. The results showed that the Brown’s LT model is more ideal and adequate for forecasting NMR in Nigeria based on the Theil’s U forecast accuracy measures of 0.001911, and that by 2030, Nigeria will have a reduced NMR of 31.5 deaths per 1,000 live births, which shows a drop to 21.5%.
On Forecasting Infant Mortality Rate by Sex using ARIMA Model: A Case of Nigeria
European Centre for Research Training and Development -UK, 2022
This paper examines the application of ARIMA model on forecasting Infant Mortality Rate (IMR) in Nigeria. It undertakes a comparison of Male and Female. The data used were obtained from the website of the World Bank. The data consist of annual Infant Mortality Rate (per 1000 live births) on Male and Female from 1980 to 2019. Akaike's Information Criterion (AIC) was used to select the best model and Time Series Plot, Residual Plot and the Histogram for Residuals were used to check the forecast adequacy of the selected models. The results of this study showed that the Infant Mortality Rate (IMR) on Male and Female attain stationarity after the second differencing. ARIMA (2,2,0) with AIC of-9.94 and ARIMA (1,2,0) with AIC of-13.10 were selected for forecasting Infant Mortality Rate for Male and Female respectively. The results further showed that the selected ARIMA models are adequate for forecasting male and female Infant Mortality Rate, and that by 2030, Male infant mortality rate will decline to 58.54 per 1000 live births while Female infant mortality rate will decline to 44.50 per 1000 live births.