| Pub. Date | : April, 2020 |
|---|---|
| Product Name | : The IUP Journal of Applied Finance |
| Product Type | : Article |
| Product Code | : IJAF20420 |
| Author Name | : Amit Kundu, Anil Kumar Goyal |
| Availability | : YES |
| Subject/Domain | : Finance |
| Download Format | : PDF Format |
| No. of Pages | : 12 |
In the present study, quarterly money plus quasi money data of India for the time period 1975-2015 is broken down by time arrangement strategies. In the study the model for M is established to be ARIMA(1, 1, 1). From the forecast obtainable by using the model, it could be observed that forecasted M is very much similar to the corresponding quarter's actual M. This is efficient in view of the test that forecast errors are white noise. Further, the results demonstrate that ARCH(2, 4) forecasting is quite better than ARIMA(1, 1, 1) forecasting. Future research should try to examine the increasingly complex determining strategies to anticipate India's quarterly money plus quasi money series.
Autoregressive Integrated Moving Average (ARIMA) was presented by Box and Jenkins in 1970s for determining a variable. ARIMA technique is an extrapolation strategy for determining and, similar to other such techniques, it requires just the verifiable time arrangement information on the variable under anticipation. Among the extrapolation techniques, this is one of the complex strategies, since it fuses the highlights of every single such strategy. It does not require the agent to pick the underlying estimations of any factor and earlier estimations of different parameters. Further, it is vigorous to deal with any information design. As one would expect, this is a difficult model to create and apply as it includes change of the variable, recognizable proof of the model, estimation through non- direct strategy, check of the model and inference of gauges. The present paper, initially clarifies the ARIMA model, and then builds an equivalent for GDP utilizing yearly information for India for the period from 1975 to 2015.