The FACTOR Procedure

The FACTOR procedure can compute estimated factor scores directly if you specify the NFACTORS= and OUT= options, or indirectly using the SCORE procedure. The latter method is preferable if you use the FACTOR procedure interactively to determine the number of factors, the rotation method, or various other aspects of the analysis. To compute factor scores for each observation by using the SCORE procedure, do the following:

• Use the SCORE option in the PROC FACTOR statement.

• Create a TYPE=FACTOR output data set with the OUTSTAT= option.

• Use the SCORE procedure with both the raw data and the TYPE=FACTOR data set.

• Do not use the TYPE= option in the PROC SCORE statement.

For example, the following statements could be used:

proc factor data=raw score outstat=fact;
run;
proc score data=raw score=fact out=scores;
run;

or

proc corr   data=raw out=correl;
run;
proc factor data=correl score outstat=fact;
run;
proc score  data=raw score=fact out=scores;
run;

For a more detailed example, see Example 79.1 in Chapter 79, The SCORE Procedure.

A component analysis (principal, image, or Harris) produces scores with mean zero and variance one. If you have done a common factor analysis, the true factor scores have mean zero and variance one, but the computed factor scores are only estimates of the true factor scores. These estimates have mean zero but variance equal to the squared multiple correlation of the factor with the variables. The estimated factor scores might have small nonzero correlations even if the true factors are uncorrelated.