Core Mathematics - Residual analysis - part 2
Residual analysis - part 2
We now need to calculate two more columns of information. We need to have
the predicted yield values from the regression equation and then we need
the residuals, the difference between the actual yield and the predicted
yield. To calculate the predicted yield we need to substitute the X values
into the regression equation. To do this, type the regression equation with
an = sign in front of it into cell c43 (in the example) and then fill down.
To calculate the residuals type then fill down. Now we need to graph the
residuals and we do this by highlighting the X values and the residual
values and following the chart wizard instructions.
There appears to be a quadratic (squared) pattern among the residuals.
This suggests that the linear model does not capture all the essential
features of the data. We therefore need to transform the data, in this case
a square transformation is indicated by the residual pattern. We then graph
x versus Y and calculate another regression line.
Previous | Next
Log in to save your progress and obtain a certificate in Alison’s free Statistics, Correlation and Regression in Mathematics online course
Sign up to save your progress and obtain a certificate in Alison’s free Statistics, Correlation and Regression in Mathematics online course
Please enter you email address and we will mail you a link to reset your password.