Box-Jenkins ARIMA Approach to Predict FDI Inflow in India
Keywords:ARIMA, Forecast, Box and Jenkins, Stationary, Foreign direct investment (FDI)
AbstractThe study attempts to model and predict the FDI inflows in India through use of time series data for FDI inflow in India from 1980 to 2019. The Autoregressive integrated moving average (ARIMA) model developed by Box and Jenkins (1976) was used to develop the model. UBJ identification included the determination of appropriate AR (autoregressive) and MA (moving-average) polynomials orders i.e. values of p and q. Orders were determined from the autocorrelation functions and partial autocorrelation functions of the stationary series. FDI data were found to be non stationary and a single order differencing was sufficient to obtain the appropriate stationary series. The study determined a low AIC value and subsequently introduced the ARIMA model (1,1,0) as a suitable FDI predictor model in India. The promised FDI inflows for the years 2016-17 to 2018-19 were within the scope of confidence and the percentage deviation of predictable and observable values ensures that our predicted prices close to real prices.
The manuscripts once accepted and published in the Indian Journal of Extension Education will automatically become the property of the Indian Society of Extension Education, New Delhi. The Chief Editor on behalf of the Indian Journal of Extension Education holds the copyright.