In: Math
How can the use of linear equations and inequalities assist you with linear regression to make predictions?
Solving the systems of linear equations is the key to access the prediction methodology by linear regression. Suppose, Y is a respone variable which is to be predicted with the help of a bunch of explainatory variable X1,X2,...,Xp. The corresponding multiple linear regression model is given by,
where is the eroor term which is assumed to be a random variable with unknown is the unknown variance.
Based on the datset the least square criterion needs minimization of,