ALISHA MITTAL*, URMIL VERMA AND MANOJ KUMAR
Department of Mathematics and Statistics, CCS Haryana Agricultural University, Hisar-125 004 (Haryana), India
*(e-mail: alishamittal602@hau.ac.in; Mobile : 89501 38848)
(Received: June 20, 2022; Accepted: July 21, 2022)
ABSTRACT
Multiple linear regression models incorporating weather variables each spanning successive fortnights
within the growth period of the cotton crop and crop condition term were developed to predict the cotton
yields in four cotton growing districts, namely, Hisar, Fatehabad, Sirsa and Bhiwani of the Haryana
state. Although, the weather variables were found statistically significant as predictors and gave predictions with reasonably high coefficients of determination (R2) but the predictions had too high per cent deviations to be acceptable and hence were deemed unsuitable for routine crop yield forecasting. To improve the predictive accuracy, a dummy variable in the form of Crop Condition Term (CCT) was added to the weather models. Addition of CCT to the weather models significantly improved the accuracies of the
cotton yield predictions.
Key words : Crop condition term, Durbin-Watson d-test, per cent deviation, weather variables