Cereals are prime determinant of agricultural status of the state mainly during kharif season. Forecasting of the production of kharif cereals is of utmost importance to formulate the agricultural policy and strategy of the state. The ARIMA model can be reliably used to forecast for short future periods because uncertainty in prediction increases when done for longer future periods. The predictions obtained from the ordinary regression model are valid only when the relationship between the independent variables and the dependent variable does not change significantly in the future period which can be rarely assumed. It is expected that the spline regression will overcome the respective discrepancies in both ARIMA and ordinary regression techniques of forecasting with the assumption that the future period which needs forecasting follows the same pattern as the last partitioned period. The entire period of data is split into different periods based on the scatter plot of the data The suitable regression models, such as, linear, compound, logarithmic and power model are fitted to the data on area and yield of kharif cereals by using the training set data. Selection of best fit model is done on the basis of overall significance of the model, model diagnostic test for error assumptions and model fit statistics. The selected best fit model is then cross validated with the testing set data. After successful cross validation of the selected best fit models, they are used for forecasting of the future values for their respective variables. The models found to be best fit and thus selected for cross validation purpose are compound spline model for both area and yield of kharif cereals respectively. Forecasting of area, yield and hence production of kharif cereals for six years ahead i.e., for the year 2020-21 to 2025-26 by using the selected best fit model after successful cross validation. The forecast values for production of kharif cereals are found to decrease despite increase in forecast values of yield which is due to decrease in forecast value of area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.