Open AccessArima forecasting of the prevalence of anemia in children in Sierra Leone
Author(s) -
Smartson. P. Nyoni,
Thabani Nyoni
Publication year - 2020
Publication title -
middle european scientific bulletin
Language(s) - English
Resource type - Journals
ISSN - 2694-9970
DOI - 10.47494/mesb.2020.4.43
Subject(s) - sierra leone , autoregressive integrated moving average , anemia , box–jenkins , time series , demography , pediatrics , statistics , econometrics , geography , medicine , mathematics , socioeconomics , economics , sociology
Using annual time series data on the prevalence of anemia in children under 5 years of age in Sierra Leone from 1990 – 2016, the study makes predictions for the period 2017 – 2025. The study applies the Box-Jenkins ARIMA methodology. The diagnostic ADF tests show that the AS series under consideration is an I (0) variable. Based on the AIC, the study presents the AR (4) model, also known as the ARIMA (4, 0, 0) model as the optimal model. The diagnostic tests further show us that the presented model is stable and its residuals are not serially correlated. The results of the study indicate that the prevalence of anemia in children in Sierra Leone will rise over the out-of-sample period. By 2025, the country will be having a prevalence of anemia in children of approximately 78.6%.