EXTRACTION Subcommand (FACTOR command)
EXTRACTION specifies the factor extraction technique.
- Only one
EXTRACTIONsubcommand is allowed. If multipleEXTRACTIONsubcommands are specified, only the last is performed. - If any
ANALYSISsubcommand is explicitly specified, allEXTRACTIONsubcommands before the lastANALYSISsubcommand are ignored. If noEXTRACTIONsubcommand is specified after the lastANALYSISsubcommand, the default extraction is performed. - If
EXTRACTIONis not specified or is included without specifications, principal components extraction is used. - If you specify criteria for
EXTRACTION, theCRITERIAsubcommand must precede theEXTRACTIONsubcommand. - When you specify
EXTRACTION, you should always explicitly specify theROTATIONsubcommand. IfROTATIONis not specified, the factors are not rotated.
PC. Principal
components analysis 1. This
is the default. PC can also
be requested with keyword PA1 or DEFAULT.
PAF. Principal
axis factoring. PAF can also be requested with keyword PA2.
ALPHA. Alpha factoring 2. Invalid if METHOD=COVARIANCE.
IMAGE. Image factoring 3.
ULS. Unweighted
least squares 4. Invalid
if METHOD=COVARIANCE.
GLS. Generalized
least squares. Invalid if METHOD=COVARIANCE.
ML. Maximum likelihood 5. Invalid if METHOD=COVARIANCE.
Example
FACTOR VARIABLES=V1 TO V12
/ANALYSIS=V1 TO V6
/EXTRACTION=ULS
/ROTATE=NOROTATE.
- This example analyzes variables V1 through V6 with an unweighted least-squares extraction. No rotation is performed.
1
Harman, H. H. 1976. Modern Factor Analysis, 3rd ed. Chicago: University
of Chicago Press.
2
Kaiser, H. F., and J. Caffry. 1965. Alpha factor analysis.
Psychometrika, 30, 1-14.
3
Kaiser, H. F. 1963. Image analysis. In: Problems in Measuring Change, C.
W. Harris, eds. Madison: University of Wisconsin Press.
4
Jöreskog, K. G. 1977. Factor analysis by least-square and maximum-likelihood
method. In: Statistical Methods for Digital Computers, volume 3, K. Enslein, A. Ralston, and
R. S. Wilf, eds. New York: John Wiley and Sons.
5
Jöreskog, K. G., and D. N. Lawley. 1968. New methods in maximum
likelihood factor analysis. British Journal of Mathematical and Statistical Psychology, 21,
85-96.