In: Math
In regards to Statistics: the exploration and and analysis of data (7th edition), chapter 13, question 43. Part a of the question asks for the equation of an estimated regression line. The solution is already on chegg, but my question is: why are SSR, Se, and Sb still calculated, after y-hat=2.7...+(0.04...)x has already been solved for?
SSR is the sum of squares due to regression, it is the sum of the squared differences between the predicted values and the mean value of y or dependent variable. It is calculated because it gives the explained sum of squares in regression if it is significantly higher than the residual sum of squares then we can say that the variability in the independent variable is capable of explaining a good amount of variability in the dependent.
The value of Se represents the standard error it is calculated because it is the accuracy measure for the regression model if the value of Se is low then the model is expected to give more accurate predictions.
The value of Sb is the standard error of the slope coefficient and it helps to test the significance of slope value. In the equation y-hat=2.7...+0.04...x, the value 0.04... is the slope and we want to check its significance because if it is significant then we can conclude that x has a significant linear relationship with y.