A Statistical Investigation on Different Modeling Techniques For Crop Yield Influenced By Weather Parameters in Northern Hills of Chhattisgarh

A statistical analysis was carried out for the period of 1974-2011 to access the better relationship between weather parameters productivity of crops like rice, maize and groundnut in Northern Hills of Chhattisgarh. The statistical tools namely different nonlinear models were used for statistical analysis. The different models were used to predict productivity of crops with the help of individual weather parameter. Models were selected on the basis of significance of the variable and R2, which explains the variation in dependent and independent variables. Nonlinear models were used for predicting yield using each weather parameter, among that power, compound, cubic, s- curve, logarithmic and quadratic models were found significant. For each crop, different model were significant but mainly quadratic and cubic model were best because of higher R2, a indicator of good relationship between dependent and independent variables.