The CANDISC Procedure

activates all the display options.

displays univariate statistics for testing the hypothesis that the class means are equal in the population for each variable.

displays between-class correlations.

displays between-class covariances. The between-class covariance matrix equals the between-class SSCP matrix divided by , where n is the number of observations and c is the number of classes. The between-class covariances should be interpreted in comparison with the total-sample and within-class covariances, not as formal estimates of population parameters.

displays the between-class SSCP matrix.

specifies the data set to be analyzed. The data set can be an ordinary SAS data set or one of several specially structured data sets created by SAS statistical procedures. These specially structured data sets include TYPE=CORR, TYPE=COV, TYPE=CSSCP, and TYPE=SSCP. If you omit the DATA= option, PROC CANDISC uses the most recently created SAS data set.

displays squared Mahalanobis distances between the group means, the F statistics, and the corresponding probabilities of greater squared Mahalanobis distances between the group means.

specifies the number of canonical variables to be computed. The value of n must be less than or equal to the number of variables. If you specify NCAN=0, the procedure displays the canonical correlations but not the canonical coefficients, structures, or means. A negative value suppresses the canonical analysis entirely. Let v be the number of variables in the VAR statement, and let c be the number of classes. If you omit the NCAN= option, only canonical variables are generated; if you also specify an OUT= output data set, v canonical variables are generated, and the last canonical variables have missing values.

suppresses the normal display of results. This option temporarily disables the Output Delivery System (ODS). For more information about ODS, see Chapter 23, Using the Output Delivery System.

creates an output SAS data set to contain the original data and the canonical variable scores. If you want to create a SAS data set in a permanent library, you must specify a two-level name. For more information about permanent libraries and SAS data sets, see SAS Programmers Guide: Essentials.

creates a TYPE=CORR output SAS data set to contain various statistics, including class means, standard deviations, correlations, canonical correlations, canonical structures, canonical coefficients, and means of canonical variables for each class. If you want to create a SAS data set in a permanent library, you must specify a two-level name. For more information about permanent libraries and SAS data sets, see SAS Programmers Guide: Essentials.

displays pooled within-class correlations (partial correlations based on the pooled within-class covariances).

displays pooled within-class covariances.

specifies a prefix for naming the canonical variables. By default the names are Can1, Can2, Can3, and so on. If you specify PREFIX=Abc, the components are named Abc1, Abc2, and so on. The number of characters in the prefix plus the number of digits required to designate the canonical variables should not exceed the length defined by the VALIDVARNAME= system option (for example, 32 for VALIDVARNAME=V7). The prefix is truncated if the combined length exceeds the maximum.

displays the pooled within-class corrected SSCP matrix.

suppresses the display of canonical structures, canonical coefficients, and class means on canonical variables; only tables of canonical correlations and multivariate test statistics are displayed.

displays simple descriptive statistics for the total sample and within each class.

specifies the criterion for determining the singularity of the total-sample correlation matrix and the pooled within-class covariance matrix, where 0 < p < 1. The default is SINGULAR=1E–8.

Let be the total-sample correlation matrix. If the R square for predicting a quantitative variable in the VAR statement from the variables that precede it exceeds 1 – p, then is considered singular. If is singular, the probability levels for the multivariate test statistics and canonical correlations are adjusted for the number of variables whose R square exceeds 1 – p.

If is considered singular and the inverse of (squared Mahalanobis distances) is required, a quasi inverse is used instead. For more information, see the section Quasi-inverse in Chapter 42, The DISCRIM Procedure.

displays total-sample and pooled within-class standardized class means.

displays total-sample correlations.

displays total-sample covariances.

displays the total-sample corrected SSCP matrix.

displays within-class correlations for each class level.

displays within-class covariances for each class level.

displays the within-class corrected SSCP matrix for each class level.