- Repeat steps 2 and 3 for those variables not yet in the model. At any
subsequent step, if none meets the criterion in step 3, no more variables
are included in the model and the process is terminated.
Backward elimination procedure - Fit the multiple regression model containing all available independent
variables: - Select the least important factor according to a certain predetermined
criterion; this is done by considering one factor at a time and treat it as
though it were the last variable to enter. - Test for the significance of the factor selected in step 2 and determine,
according to a certain predetermined criterion, whether or not to delete
this factor from the model. - Repeat steps 2 and 3 for those variables still in the model. At any sub-
sequent step, if none meets the criterion in step 3, no more variables are
removed in the model and the process is terminated.
Stepwise regression procedure. Stepwise regression is a modified version
of forward regression that permits reexamination, at every step, of the
variables incorporated in the model in previous steps. A variable entered
at an early stage may become superfluous at a later stage because of its
relationship with other variables now in the model; the information it
provides becomes redundant. That variable may be removed, if meeting
the elimination criterion, and the model is refitted with the remaining var-
iables, and the forward process goes on. The entire process, one step for-
ward followed by one step backward, continues until no more variables
can be added or removed.
Criteria For the first step of the forward selection procedure, decisions are
based on individual score test results [ttest,ðn 2 Þdf ]. In subsequent steps,
both forward and backward, the decision is made as follows. Suppose that
there arerindependent variables already in the model and a decision is needed
in the forward selection process. Two regression models are now fitted, one
with allrcurrentX’s included to obtain the regression sum of squares (SSR 1 )
and one with allrX’s plus theXunder investigation to obtain the regression
sum of squares (SSR 2 ). Define the mean square due to addition (or elimination)
as
MSR¼
SSR 2 SSR 1
1
Then the decision concerning the candidate variable is based on
F¼
MSR
MSE
anFtest atð 1 ;nr 1 Þdegrees of freedom.
304 CORRELATION AND REGRESSION