Modelling and Prediction of Outpatients Department on Hospital Attendance at the Cape Coast Teaching Hospital Using the Box-Jerkins ARIMA Model
Journal of Advances in Mathematics and Computer Science · pp. 1–12 · Published 30 Oct 2020
10.9734/jamcs/2020/v35i830309Abstract
Aims: Outpatient department is one of the first points of contact for patients accessing health care and provide patients with their primary healthcare as they seek services at the facility. With the introduction of community-based health planning and services, there seems that the outpatient departments have witnessed corresponding progressive and significant increase in attendance at the various health facilities in Ghana of which the research seeks to investigate. Materials and Methods: The data collected were outpatient hospital attendance of patients on a monthly basis from 2012 to 2019 obtained from the Cape Coast Teaching Hospital. Box Jenkins’s methodology of time series analysis was used to analyse the data. The modified Box Pierce (Ljumg-Box) Chi-square statistic criteria of the largest and minimum Chi-square statistic value was in selecting the best fitted model for outpatient department attendance. Results: The autocorrelation function (ACF) and partial autocorrelation function (PACF) plots suggested an autoregressive (AR) process with order 2 and moving average (MA) process with order 1 which was used in selecting the appropriate model. Candidate models were obtained using the lowest Chi-square value and highest value to select adequate models and the best model. The best non-seasonal model for the data was ARIMA (2, 2, 1) for the outpatient department attendance. Model diagnostics test was performed using Ljung-Box test. Conclusion: The findings of the forecast showed that OPD visits will increase in the next five years. Specifically, continued use of the outpatient department in accessing health care at all levels will experience an increase in hospital visits across the months from June 2020 to December 2025. Recommendations from this research included among others that, the health authorities should continue to expand the outpatient department services to increase access to healthcare by all as it services goes to the core people in the community.
References (6)
- 1 Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root [DOI]
- 2 Time Series Analysis: Forecasting and Control [DOI]
- 3 Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models [DOI]
- 4 Statistical Analysis of Health Insurance and Cash and Carry Systems in Cape Coast Teaching Hospital of Ghana [DOI]
- 5 2016 Annual Report of the ABPN [DOI]
- 6 MODELLING AND FORECASTING INFLATION RATES IN GHANA: AN APPLICATION OF SARIMA MODELS
Cited by 1
M. Bakr, J. Prah, K. S. Nkrumah · Journal of Advances in Mathematics and Computer Science · 2021
Related research
- Time-Series Modeling and Short Term Prediction of Annual Temperature Trend on Coast Libya Using the Box-Jenkins ARIMA Model — shares topic coverage
- Threat to the Sustainable Production of Natural Resins: A Case of Rangeeni Strain of Kerria lacca (Kerr) in Eastern Plateau & Hills Region of South East Asia — shares topic coverage
- Forecasting Student Enrollment Trends in Hotel Catering and Institutional Management at Kumasi Technical University — shares topic coverage
- Spatio-temporal Analysis of Land Cover Changes of Izmir Province of Turkey Using Landsat TM and OLI Imagery — shares topic coverage
- Automating Behavior? An Experimental Living Lab Study on the Effect of Smart Home Systems and Traffic Light Feedback on Heating Energy Consumption — shares topic coverage
Article metrics
Real usage data collected on this platform.
31
Page views
0
PDF downloads
0
Outbound clicks
1
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.