Extracts common factors. The faExtract action is part of the Factor Analysis action set and provides functionality to perform factor analysis using various extraction methods such as Principal Component Analysis, Maximum Likelihood, and others. It supports handling of priors, rotation of factors, and handling of Heywood cases.
| Parameter | Description |
|---|---|
| attributes | Changes the attributes of variables used in this action. |
| corrOut | Specifies an output table to contain the correlation matrix, summary statistics, and number of observations data. |
| display | Specifies a list of results tables to send to the client for display. |
| freq | Specifies a numeric variable that contains the frequency of occurrence of each observation. |
| fuzz | Specifies a minimum threshold that determines whether to print correlations and factor loading values. Values less than the threshold are treated as missing. |
| inputs | Specifies the input variables to use for analysis. |
| method | Specifies the method to be used for factor extraction (e.g., ALPHA, ML, PRINCIPAL, PRINIT, ULS). |
| nFactors | Specifies the number of factors to be extracted for each BY group. |
| outputTables | Lists the names of results tables to save as CAS tables on the server. |
| priors | Specifies the method of computing prior communality estimates (e.g., SMC, MAX, RANDOM). |
| referenceStructure | When set to True, requests output tables that are related to the reference structure (only for oblique rotations). |
| reorder | When set to True, reorders the rows (variables) of various factor matrices in the output based on absolute loading values. |
| rotate | Specifies the method to use for factor rotation (e.g., VARIMAX, PROMAX, OBLIMIN). |
| table | Specifies the settings for the input table. |
| varianceDivisor | Specifies the variance divisor for calculating variances and covariances (DF, N, WDF, WEIGHT). |
| weight | Specifies a numeric variable to use as a weight to perform a weighted analysis of the data. |
Creates a dataset 'socio_economics' containing socio-economic indicators for analysis.
| 1 | PROC CAS; |
| 2 | dataStep.runCode / code=" |
| 3 | data casuser.socio_economics; |
| 4 | input Population Schooling Employment Services HouseValue; |
| 5 | datalines; |
| 6 | 5700 12.5 85 5 25000 |
| 7 | 1000 10.0 70 2 15000 |
| 8 | 3000 11.0 75 3 20000 |
| 9 | 8000 14.0 90 8 35000 |
| 10 | 6000 12.0 80 6 27000 |
| 11 | 4500 11.5 78 4 22000 |
| 12 | ; |
| 13 | run; |
| 14 | "; |
| 15 | RUN; |
Performs a simple factor analysis using the default Principal Component method extracting 1 factor.
| 1 | PROC CAS; |
| 2 | factorAnalysis.faExtract / |
| 3 | TABLE={name="socio_economics", caslib="casuser"}, |
| 4 | nFactors=1; |
| 5 | RUN; |
Performs factor analysis using Maximum Likelihood estimation, extracts 2 factors, applies Varimax rotation, and uses Squared Multiple Correlations (SMC) for priors.
| 1 | PROC CAS; |
| 2 | factorAnalysis.faExtract / |
| 3 | TABLE={name="socio_economics", caslib="casuser"}, |
| 4 | method={name="ML", maxIterations=50}, |
| 5 | nFactors=2, |
| 6 | priors={type="SMC"}, |
| 7 | rotate={type="VARIMAX"}, |
| 8 | outputTables={names={"FactorPattern", "Eigenvalues", "RotatedFactorPattern"}}; |
| 9 | RUN; |