The normal plot with residue and the plots of residuals versus
predicted were analysed and shown in Fig. 1(a) and (b). In the
normal probability plot of the raw data, the analysis of variance
shows a more effective (straightforward) relationship with the residuals.
The quadratic polynomial model satisfies the assumptions
analysis of variance (ANOVA) (the error distribution) is approximately
normal (Fig. 1(a)). If the model is correct and the assumptions
are satisfied, the residuals should have no structure. In
particular, they should be unrelated to any other variable including
the predicted response. A simple check would include plotting the
residuals versus the fitted (predicted) values. A plot of the residuals
versus the rising predicted response values tests the assumption of
the constant variance. The plot shows random scatter, which justifies
the need for no alteration to minimize personal error
(Fig. 1(b)).