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

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

GENLOG 609<br />

• To separate the independent variables from the dependent variables in a logit model, use<br />

the keyword BY. The categorical variables preceding BY are the dependent variables; the<br />

categorical variables following BY are the independent variables.<br />

• Up to 10 variables can be specified, including both dependent and independent variables.<br />

• For the logit model, you must specify MULTINOMIAL on the MODEL subcommand.<br />

• GENLOG displays an analysis of dispersion and two measures of association—entropy<br />

and concentration. These measures are discussed in Haberman (1982) and can be used to<br />

quantify the magnitude of association among the variables. Both are proportionalreduction-in-error<br />

measures. The entropy statistic is analogous to Theil’s entropy<br />

measure, while the concentration statistic is analogous to Goodman and Kruskal’s tau-b.<br />

Both statistics measure the strength of association between the dependent variable and the<br />

independent variable set.<br />

Example<br />

GENLOG GSLEVEL BY EDUC SEX<br />

/MODEL=MULTINOMIAL<br />

/DESIGN=GSLEVEL, GSLEVEL BY EDUC, GSLEVEL BY SEX.<br />

• The keyword BY on the variable list specifies a logit model in which GSLEVEL is the<br />

dependent variable and EDUC and SEX are the independent variables.<br />

• A logit model is multinomial.<br />

• DESIGN specifies a model that can test for the absence of the joint effect of SEX and EDUC<br />

on GSLEVEL.<br />

Cell Covariates<br />

• Continuous variables can be used as covariates. When used, the covariates must be specified<br />

after the WITH keyword following the list of categorical variables.<br />

• A variable cannot be named as both a categorical variable and a cell covariate.<br />

• To enter cell covariates into a model, the covariates must be specified on the DESIGN<br />

subcommand.<br />

• Cell covariates are not applied on a case-by-case basis. The weighted covariate mean for<br />

a cell is applied to that cell.<br />

Example<br />

GENLOG DPREF RACE CAMP WITH X<br />

/DESIGN=DPREF RACE CAMP X.<br />

• The variable X is a continuous variable specified as a cell covariate. Cell covariates must<br />

be specified after the keyword WITH following the variable list. No range is defined for<br />

cell covariates.<br />

• To include the cell covariate in the model, the variable X is specified on DESIGN.

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

Saved successfully!

Ooh no, something went wrong!