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.

GENLOG 615<br />

• The saved variables are pertinent to cells in the contingency table, not to individual<br />

observations. In the Data Editor, all cases that define one cell receive the same value. To<br />

make sense of these values, you need to aggregate the data to obtain cell counts.<br />

Example<br />

GENLOG A B<br />

/SAVE PRED (PREDA_B)<br />

/DESIGN = A, B.<br />

• SAVE saves the predicted values for two independent variables A and B.<br />

• The saved variable is renamed PREDA_B and added to the working data file.<br />

DESIGN Subcommand<br />

DESIGN specifies the model to be fit. If DESIGN is omitted or used with no specifications, the<br />

saturated model is produced. The saturated model fits all main effects and all interaction effects.<br />

• Only one design can be specified on the subcommand.<br />

• To obtain main-effects models, name all of the variables listed on the variables<br />

specification.<br />

• To obtain interactions, use the keyword BY or an asterisk (*) to specify each interaction, for<br />

example, A BY B or C*D. To obtain the single-degree-of-freedom partition of a specified<br />

factor, specify the partition in parentheses following the factor (see the example below).<br />

• To include cell covariates in the model, first identify them on the variable list by naming<br />

them after the keyword WITH, and then specify the variable names on DESIGN.<br />

• Effects that involve only independent variables result in redundancy. GENLOG removes<br />

these effects from the model.<br />

• If your variable list includes a cell covariate (identified by the keyword WITH), you cannot<br />

imply the saturated model by omitting DESIGN or specifying it alone. You need to request<br />

the model explicitly by specifying all main effects and interactions on DESIGN.<br />

Example<br />

COMPUTE X=MONTH.<br />

GENLOG MONTH WITH X<br />

/DESIGN X.<br />

• This example tests the linear effect of the dependent variable.<br />

• The variable specification identifies MONTH as a categorical variable. The keyword WITH<br />

identifies X as a covariate.<br />

• DESIGN tests the linear effect of MONTH.<br />

Example<br />

GENLOG A B<br />

/DESIGN=A.<br />

GENLOG A B<br />

/DESIGN=A,B.

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

Saved successfully!

Ooh no, something went wrong!