The CALIS Procedure

GROUP Statement

  • GROUP i </ options>;

where i is an assigned group number between 1 and 9999, inclusively.

The GROUP statement signifies the beginning of a group specification block and designates a group number for the group. All subsidiary group specification statements after a GROUP statement belong in that group until another MODEL or GROUP statement is used. The subsidiary group specification statements refer to one of the following four statements:

For example, consider the following statements:

proc calis;
   var X1-X4;
   group 1 / label='Women' data=women_data;
      freq  Z;
   group 2 / label='Men' data=men_data;
      partial P;
   model 1 / group = 1-2;
      factor N=1; /* One factor exploratory factor analysis */
run;

In the GROUP statements, two groups are defined. Group 1, labeled as 'Women', refers to the data set women_data. Group 2, labeled as 'Men', refers to the data set men_data. Both groups are fitted by an exploratory factor model defined in Model 1, as indicated in the GROUP= option of the MODEL statement. While the frequency variable Z defined in the FREQ statement is applicable only to Group 1, the partial variable P defined in the PARTIAL statement is applicable only to Group 2. However, the VAR statement, which appears before the definitions of both groups, applies globally to both Group 1 and Group 2. Therefore, variables X1X4 are the analysis variables in the two groups.

You can set group-specific options in each GROUP statement. All but one (that is, the LABEL= option) of these options are also available in the MODEL and PROC CALIS statements. If you set these group-specific options in the PROC CALIS statement, they will apply to all groups unless you respecify them in the GROUP statement. If you set these group-specific options in the MODEL statement, they will apply to all groups that are fitted by the associated model. In general, the group-specific options are transferred from the PROC CALIS statement to the MODEL statements (if present) and then to the fitted groups. In the transferring process, options are overwritten by the newer ones. If you want to apply some group-specific options to a particular group only, you should set those options in the GROUP statement corresponding to that group.

Option Available in the GROUP Statement Only

LABEL=name
NAME=name

specifies a label for the current group. You can use any valid SAS names up to 256 characters for labels. You can also use quote strings for the labels. This option can be specified only in the GROUP statement, not the PROC CALIS statement.

Options Available in the GROUP and PROC CALIS Statements

These options are available in the GROUP and PROC CALIS statements:

Option

Description

DATA=

Specifies the input data set

INWGT=

Specifies the data set that contains the weight matrix

OUTSTAT=

Specifies the data set for storing the statistical results

OUTWGT=

Specifies the data set for storing the weight matrix

ROBITER=

Specifies the maximum number of iterations for estimating robust covariance and mean matrices

ROBPHI=

Specifies the tuning parameter for robust methods

See the section PROC CALIS Statement Options for more details about these options. If you specify these options in the PROC CALIS statement, they are transferred to all GROUP statements. They might be overwritten by the respecifications in the individual GROUP statements.

Options Available in GROUP, MODEL, and PROC CALIS Statements

These options are available in the GROUP, MODEL , and PROC CALIS statements:

Option

Description

ALPHALEV=

Specifies the $\alpha $-level criterion for detecting leverage points

ALPHAOUT=

Specifies the $\alpha $-level criterion for detecting outliers

BIASKUR

Computes the skewness and kurtosis without bias corrections

EDF=

Defines nobs by the number of error df

INWGTINV

Specifies that the INWGT= data set contains the inverse of the weight matrix

KURTOSIS

Computes and displays kurtosis

MAXMISSPAT=

Specifies the maximum number of missing patterns to display

NOBS=

Defines the number of observations (nobs)

NOMISSPAT

Suppresses the display of missing pattern analysis

PCORR

Displays analyzed and estimated moment matrix

PLOTS=

Specifies ODS Graphics selection

PWEIGHT

Displays the weight matrix

RDF | DFR=

Defines nobs by the number of regression df

RESIDUAL | RES

Computes the default residuals

RESIDUAL | RES=

Specifies the type of residuals

RIDGE

Specifies the ridge factor for covariance matrix

SIMPLE

Prints univariate statistics

TMISSPAT=

Specifies the data proportion threshold for displaying the missing patterns

VARDEF=

Specifies variance divisor

WPENALTY=

Specifies the penalty weight to fit correlations

WRIDGE=

Specifies the ridge factor for the weight matrix

If you specify these options in the PROC CALIS statement, they are transferred to all MODEL statements. These options are overwritten by the respecifications in the individual MODEL statements. After these options are resolved in a given MODEL statement, they are transferred further to the GROUP statements of which the associated groups are fitted by the model. Again, these options might be overwritten by the respecifications in the individual GROUP statements.