Abstract:
Time series is a set of observations measured at a successive interval of time. It involves
the projection of future values of a variable based entirely on the past and present
observations of that variable. The first step in time series analyses is the time plot. Time
series models such as, the linear trend analysis, exponential trend analysis, parabolic
trend analysis; Yule Walker ami Holt - Winters forecasting models were reviewed,
The comparative study of these models was made. The principle of parsimony is
used to get the best fit out of the linear, exponential and parabolic trends. Model
identification is applied to the Autoregressive Process of order p, Moving Average
Process of order q and the Autoregressive Moving Average Process of order p and q.
Functions used for the model identification are autocorrelation and partial
autocorrelation.
The mathematical model of the time series analyses is presented. A Knowledge
Based Server far the Time Series Analyses of Agricultural Products is designed and
implemented. J\ case study of rice production in Nigeria from 1966 to 1996 is carried out
aJ1L'projection made to the year 2006. The result obtained from the case study proved to
be meaningful in practice.
ii
