DFFITS stands for “difference in fits”. It is calculated by measuring the change in predicted values that occurs when that response value is deleted. The larger the value of DFFITS, the more it influences the fitted model. Another way to explain DFFITS is it is the externally Studentized residuald magnified at high leverage points and shrunk by low leverage points.
A run is considered influential when the value of the DFFITS is outside the limits.
The limits are computed as…
Where n is the number of runs in the design, and p is the number of terms in the model.
Use the DFFITS to judge the influence of suspected outliers.
Never ignore a run just because the diagnostics plots indicate it may be a problem. Verify that the data is wrong in some way before ignoring it.