Stochastic population forecast for Kenya: Arima model approach
Abstract
Trends in population have important implications for a government 111 planning and
formulating its manpower-related policies. A business may also need to adjust its long-term
market strategies according to these trends. Nonetheless, today, the tremendous increase in
population is the major issue of the world. In this empirical study, population of Kenya from
1960 to 2009 is modeled using Box Jenkins arima methodology. The population of Kenya is
also forecasted for the next 20 years using the parsimonious arima (1, 2, 2), model. If the
current growth rate trend continues, the population of Kenya would be approximately 65.08
by 2029. The model was validated by the criteria of AIC, Ljung-Box test, P-values and
graphical techniques e.g. ACF and PACF plots of residuals. The projected population by
parsimonious arima model is close to the projected population of Kenya by different bureaus
(CIA) but there is a notable wide gap with projections from KNBS
In addition, the results shows that the population growth rate will be at 4.273 by year 2029 as
the population will be approaching 65.0819 million. Further, the results depict a negative
trend on crude death rate while the crude birth rate has a positive trend and a steady growth
as we get to 2029.
Citation
Master of Science (Social Statistics)Publisher
University of Nairobi School of Mathematics