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.

854 MANOVA: Univariate<br />

HOMOGENEITY Keyword<br />

HOMOGENEITY requests tests for the homogeneity of variance of the dependent variable<br />

across the cells of the design. You can specify one or more of the following specifications in<br />

parentheses. If HOMOGENEITY is requested without further specification, the default is ALL.<br />

BARTLETT Bartlett-Box F test.<br />

COCHRAN Cochran’s C.<br />

ALL Both BARTLETT and COCHRAN. This is the default.<br />

DESIGN Keyword<br />

You can request the following by entering one or more of the specifications in parentheses<br />

following the keyword DESIGN. If DESIGN is requested without further specification, the<br />

default is OVERALL.<br />

The DECOMP and BIAS matrices can provide valuable information on the confounding<br />

of the effects and the estimability of the chosen contrasts. If two effects are confounded, the<br />

entry corresponding to them in the BIAS matrix will be nonzero; if they are orthogonal, the<br />

entry will be zero. This is particularly useful in designs with unpatterned empty cells. For<br />

further discussion of the matrices, see Bock (1985).<br />

OVERALL The overall reduced-model design matrix (not the contrast matrix). This is<br />

the default.<br />

ONEWAY The one-way basis matrix (not the contrast matrix) for each factor.<br />

DECOMP The upper triangular QR/CHOLESKY decomposition of the design.<br />

BIAS Contamination coefficients displaying the bias present in the design.<br />

SOLUTION Coefficients of the linear combinations of the cell means used in significance<br />

testing.<br />

REDUNDANCY Exact linear combinations of parameters that form a redundancy. This<br />

keyword displays a table only if QR (the default) is the estimation method.<br />

COLLINEARITY Collinearity diagnostics for design matrices. These diagnostics include the<br />

singular values of the normalized design matrix (which are the same as<br />

those of the normalized decomposition matrix), condition indexes corresponding<br />

to each singular value, and the proportion of variance of the corresponding<br />

parameter accounted for by each principal component. For<br />

greatest accuracy, use the QR method of estimation whenever you request<br />

collinearity diagnostics.<br />

ALL All available options.

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

Saved successfully!

Ooh no, something went wrong!