Previous Page | Next Page

The REG Procedure

Model Fit and Diagnostic Statistics

This section gathers the formulas for the statistics available in the MODEL, PLOT, and OUTPUT statements. The model to be fit is , and the parameter estimate is denoted by . The subscript denotes values for the th observation, the parenthetical subscript means that the statistic is computed by using all observations except the th observation, and the subscript indicates the th diagonal matrix entry. The ALPHA= option in the PROC REG or MODEL statement is used to set the value for the statistics.

Table 73.8 contains the summary statistics for assessing the fit of the model.

Table 73.8 Formulas and Definitions for Model Fit Summary Statistics

Definition or Formula

the number of observations

the number of parameters including the intercept

1 if there is an intercept, 0 otherwise

the estimate of pure error variance from the SIGMA=
option or from fitting the full model

the uncorrected total sum of squares for the dependent
variable

the total sum of squares corrected for the mean for the
dependent variable

the error sum of squares

the sum of squares of (see Table 73.9)

Table 73.9 contains the diagnostic statistics and their formulas; these formulas and further information can be found in Chapter 4, Introduction to Regression Procedures, and in the section Influence Statistics. Each statistic is computed for each observation.

Table 73.9 Formulas and Definitions for Diagnostic Statistics

Formula

PRED ()

RES ()

H ()

STDP

STDI

STDR

LCL

STDI

LCLM

STDP

UCL

STDI

UCLM

STDP

STUDENT

RSTUDENT

COOKD

COVRATIO

DFFITS

DFBETAS

PRESS()

Previous Page | Next Page | Top of Page