CHANDEL, ASHUDHIVYANHARSINI D2021-10-302021-10-302021-10https://krishikosh.egranth.ac.in/handle/1/5810177563ABSTRACT The present investigation was carried out to forecast the area and production of rice and wheat crops in Himachal Pradesh. The secondary data on area and production of rice crop for 30 years (1989-1990 to 2018-2019) and for wheat crop 50 years (1969-1970 to 2018-2019) were used for analysis. Various linear, non-linear and ARIMA models were employed. Most appropriate regression models were selected on the basis of significant regression coefficients, maximum values of adjusted , minimum values of RMSE, Theil’s U coefficient and non-significant F-statistic (chow test). The ARIMA models with different p, d and q were judged on the basis of auto correlation function (ACF) and partial auto correlation function (PACF) at various lags. ARIMA models were selected on the basis of various goodness of fit criteria viz., Akaike’s information criterion, Bayesian information criterion, RMSE, MAE, MAPE and Ljung-Box Q-statistic. Quadratic model was found to be the best fitted model for the estimation of area under rice and wheat crops. The cubic and linear models were found to be the appropriate model for the estimation of production of rice and wheat crops respectively. Among the ARIMA families of time series models for prediction of area and production of rice, ARIMA (0, 2, 1) and ARIMA (1, 1, 1) was found suitable whereas ARIMA (3, 1, 1) and ARIMA (2, 1, 2) models were found as the best model for the area and production of wheat in Himachal Pradesh. Forecasting was done up to 2019-2020. Forecasted values showed an increasing pattern in production of rice and wheat crops, whereas decreasing pattern was noticed in area of these crops. These forecasts would be helpful for policy makers to foresee ahead of time the future requirements of grain storage, import-export and adopt appropriate measures to increase production with a decrease in area by adopting improved agriculture practices in this regard.EnglishThesis