International Journal of Physics and Mathematics

Vol. 1, Issue 1, Part A (2019)

Time series modeling of poultry mortality rate in Ghana: West Africa


Belle AS, Ninkuu V, Achana J

In this study, data on monthly mortality rate and weather variables of average temperature and rainfall were obtained from the Ministry of Agriculture in the Upper West Region and the Meteorological Service Department of Ghana and these were modelled using both Autoregressive integrated moving average (ARIMA) and Autoregressive integrated moving average model with errors (ARIMAX). The results revealed that, regression with ARIMAX (2, 1, 1) model was the best model for the mortality rate. This model had the least AIC, BIC and HQIC values. Furthermore ARIMA (2, 1, 1) model was also identified as the best regression model. Diagnostic checks of both models, using the Ljung-Box test and ARCH-LM test, revealed that both models were free from higher-order serial correlation and conditional heteroscedasticity respectively. All variables under study were best modelled using the log-quadratic trend while rainfall followed a log-linear trend model.

Pages: 25-30  |  1177 Views  552 Downloads

How to cite this article:
Belle AS, Ninkuu V, Achana J. Time series modeling of poultry mortality rate in Ghana: West Africa. Int. J. Phys. Math. 2019;1(1):25-30.