influence

# influence - Influence Statistics Outliers and Collinearity...

This preview shows pages 1–2. Sign up to view the full content.

Influence Statistics, Outliers, and Collinearity Diagnostics Standardized Residuals – Residuals divided by their estimated standard errors (like t -statistics). Observations with values larger than ' , 2 p n n t - α in absolute value are considered outliers. thh ii ii i i i v sidual MS s v s e r = - = Re 1 diagonal element of P Studentized Residuals – Similar to standardized residuals, except ) ( ) ( Re i i sidual MS s = is computed on the regression fit on the remaining n -1 cases. Observations with values larger than 1 ' , 2 - - p n n t in absolute value are considered outliers thh ii i ii i i i i v sidual MS s v s e r = - = ) ( ) ( * Re 1 diagonal element of P These are labelled as RSTUDENT by SAS. Leverage Values (Hat Diag) – Measure of how far an observation is from the others in terms of the levels of the independent variables (not the dependent variable). Observations with values larger than 2p’/n are considered to be potentially highly influential. th ii i v diagonal element of P DFFITS – Measure of how much an observation has effected its fitted value from the regression model. Values larger than

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 2

influence - Influence Statistics Outliers and Collinearity...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online