ABSTRACT

 Obviously, the global economic crisis has led to the shortage of financial resources and to a eneral downturn in stock prices across the globe . orecasting stock prices will provide a way to anticipate and perhaps avoid the risk of a large adverse change in prices. 'his work models and forecasts stock prices of the Nigerian stock exchange using the autoregressive integrated moving ave.rage (p,d,q) model. The r.ox-Jenkins procedure for {fitting ARIMA model was adopted in the analysis of the series. Thus, the monthly All-share :. indices of the Nigerian stock exchange from January 1992 to December 2014 provides the fit sample. The log transformation was applied on the series which in essence was to stabilize the variance. Consequently, the Akaike Information Criterion was adopted for the selection of appropriate model. Hence the suggested model, ARIMA 3,1,1 modelled as: X, = 0.4521X,,- 0.2527X,% - 0.2683X,,- 0.6293e, .4 + e, was found to be adequate for describing the performance of the transformed series. Several diagnostic test were performed to select the p, d, q parameter that best fits the index. The model was subjected to test of adequacy using the AC and PAC of the residual. Hence the adequacy of the selected ARIMA(3,1,1) model was questioned by generating a year forecast.