Standardized residuals ˜ri in function of leverage li

  • Leverage li is a measure of how far away the independent variable values of an observation are from those of the other observations.

  • Data points with large residuals (outliers) and/or high leverage may distort the outcome and accuracy of a regression.

  • The predicted sum-of-squares:

PRESS=ni=1(ˆyi(i)yi)2=ni=1r2i(1li)2
  • Cook’s distance measures the effect of deleting a given observation.