DFITS

Measures the influence of each observation on the fitted values in a regression and ANOVA model. Influential observations have a disproportionate impact on the model and can produce misleading results. For example, a significant coefficient may appear to be nonsignificant. Influential observations can be leverage points, outliers, or both.

DFITS represents roughly the number of standard deviations that the fitted value changes when each observation is removed from the data set and the model is refit. Investigate observations with DFITS values greater than 2*sqrt(p / n), where p is the number of model terms (including the constant) and n is the number of observations.

To determine the extent of influence, you can fit the model with and without the influential observation and compare the coefficients, p-values, R2, and other model parameters. If the model changes significantly when you remove the influential observation, first, determine whether the observation is a data entry or measurement error. If not, examine the model further to determine if you omitted an important term (for example, an interaction term) or variable, or have incorrectly specified the model. You may need to gather more data to resolve the issue.