Data analytics and predictions in crop yielding

Regression technique can be best suited for predications in agriculture. In this paper regression analysis models the relationship between factors like plant height and tiller number which are independent variables with the yields of a crop (like rice plant) which is a dependent variable that we want to predict. In data mining independent variables are attributes already known and response variables are what we want to predict. Data analytics here involves regression analysis with more than one independent variable which is called multiple regression analysis. When all independent variable are assumed to affect the dependent variable in a linear proportion and independently of one another, the procedure is called multiple linear regression analysis. The simple liner regression and correlation analysis has one major limitation. That is applicable only to cases with one independent variable. There is a corresponding increase in need for use of regression procedures that can simultaneously handle several independent variables. Thus, the combined linear effects of plan height and tiller number with the variation in yield can be predicted with the computation of F values from Test of significance. The idea can be extended for many software based predictions where the computational steps of SSR and SSE can be derived from the outputs of software coding with saving of time and accuracy when number of samples increase with more independent variables in Big data analytics