27.03.2013 Views

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

1068 NOMREG<br />

B are factors. The expression A WITHIN B is equivalent to A(B). Factors inside a nested<br />

effect must be distinct. Expressions like A(A) and A(B*A) are invalid.<br />

• Multiple-level nesting is supported. For example, A(B(C)) means that B is nested within<br />

C, and A is nested within B(C). When more than one pair of parentheses is present, each<br />

pair of parentheses must be enclosed or nested within another pair of parentheses. Thus,<br />

A(B)(C) is not valid.<br />

• Nesting within an interaction effect is valid. For example, A(B*C) means that A is nested<br />

within B*C.<br />

• Interactions among nested effects are allowed. The correct syntax is the interaction followed<br />

by the common nested effect inside the parentheses. For example, interaction between<br />

A and B within levels of C should be specified as A*B(C) instead of A(C)*B(C).<br />

• To include a covariate term in the model, enter the name of the covariate on the MODEL<br />

subcommand.<br />

• Covariates can be connected, but not nested, using the keyword BY or the asterisk (*)<br />

operator. For example, X*X is the product of X and itself. This is equivalent to a covariate<br />

whose values are the square of those of X. However, X(Y) is invalid.<br />

• Factor and covariate effects can be connected in many ways. No effects can be nested<br />

within a covariate effect. Suppose A and B are factors, and X and Y are covariates.<br />

Examples of valid combination of factor and covariate effects are A*X, A*B*X, X(A),<br />

X(A*B), X*A(B), X*Y(A*B), and A*B*X*Y.<br />

• A stepwise method can be specified by following the model effects with a vertical bar (|),<br />

a stepwise method keyword, an equals sign (=), and a list of variables (or interactions or<br />

nested effects) for which the method is to be used.<br />

• If a stepwise method is specified, then the TEST subcommand is ignored.<br />

• If a stepwise method is specified, then it begins with the results of the model defined on<br />

the left side of the MODEL subcommand.<br />

• If a stepwise method is specified, but no effects are specified on the left side of the MODEL<br />

subcommand, then the initial model contains the intercept only (if INTERCEPT = IN-<br />

CLUDE) or the initial model is the null model (if INTERCEPT = EXCLUDE).<br />

• The intercept cannot be specified as an effect in the stepwise method option.<br />

• For all stepwise methods, if two effects have tied significance levels, then the removal or<br />

entry is performed on the effect specified first. For example, if the right side of the MOD-<br />

EL subcommand specifies FORWARD A*B A(B), where A*B and A(B) have the same significance<br />

level less than PIN, then A*B is entered because it is specified first.<br />

The available stepwise method keywords are:<br />

BACKWARD Backward elimination. As a first step, the variables (or interaction effects or<br />

nested effects) specified on BACKWARD are entered into the model together<br />

and are tested for removal one by one. The variable with the largest significance<br />

level of the likelihood-ratio statistic, provided that the value is larger<br />

than POUT, is removed, and the model is re-estimated. This process continues<br />

until no more variables meet the removal criterion, or when the current<br />

model is the same as a previous model.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!