DATA_STRUCTURE Subcommand (GENLINMIXED command)

The DATA_STRUCTURE subcommand specifies the subject structure for repeated measurements and how the errors of the repeated measurements are correlated. If the DATA_STRUCTURE subcommand is not specified, then the model assumes that all error terms are independent.

  • Records with missing values for any field on the DATA_STRUCTURE subcommand are not used in the analysis.

SUBJECTS Keyword

The SUBJECTS keyword identifies subjects in the active dataset. Complete independence is assumed across subjects, but responses within subjects are assumed to be correlated.

  • Specify a single categorical field or a list of categorical fields connected by asterisks (*) or the keyword BY.
  • The number of subjects equals the number of distinct combinations of values of the fields.
  • Any field specified on the SUBJECTS keyword cannot be used as a REPEATED_MEASURES field or on the FIELDS subcommand.
  • The SUBJECTS keyword is required if the DATA_STRUCTURE subcommand is used.

REPEATED_MEASURES Keyword

The REPEATED_MEASURES keyword gives the repeated (or within-subject) effect. This effect defines the ordering of repeated measurements within subjects. If some measurements do not appear in the data for some subjects, then the existing measurements are ordered and the omitted measurements are treated as missing values. If REPEATED_MEASURES is not specified, then no repeated measures model is built.

  • Specify a single field or a list of fields connected by asterisks (*) or the keyword BY.
  • Each distinct combination of the values of the fields defines a separate repeated measure.
  • Any field specified on the REPEATED_MEASURES keyword cannot be used as a SUBJECTS keyword or on the FIELDS subcommand.
  • Each distinct repeated measures value must occur only once within a subject. Generally speaking, you should not use a WEIGHT field if REPEATED MEASURES is specified.

KNONECKER_MEASURES Keyword

The Kronecker product of two matrices can handle doubly repeated-measure data in which there are two repeated effects; one of them indicating the multivariate observation of target, and the other the time or the order of the data measured. The KNONECKER_MEASURES keyword should be only when COVARIANCE_TYPE is defined as UN_AR1, UN_CS, or UN_UN. When both KRONECKER_MEASURES and REPEATED_MEASURES keywords are in effect, they may or may not have common fields, but their values cannot be exactly the same (even when the values are not in the same order).

GROUPING Keyword

The GROUPING keyword allows you to define independent sets of covariance parameters. All subjects have the same covariance type; subjects within the same covariance grouping will have the same values for the parameters.

  • Specify a single categorical field or a list of categorical fields connected by asterisks (*) or the keyword BY.
  • Each distinct combination of the values of the fields defines a separate covariance grouping.
  • A field specified on the GROUPING keyword can also be used as a SUBJECTS or REPEATED_MEASURES field, the TARGET on the FIELDS subcommand, or on the EFFECTS keyword or the FIXED or RANDOM subcommand.
  • The GROUPING keyword is optional.
  • If the GROUPING keyword is used, there must also be a REPEATED_MEASURES specification.

COVARIANCE_TYPE Keyword

The COVARIANCE_TYPE keyword gives the covariance structure of the residual covariance matrix.

AR1. First-order autoregressive.

ARH1. Heterogenous first-order autoregressive.

ARMA11. Autoregressive moving average (1,1).

COMPOUND_SYMMETRY. This structure has constant variance and constant covariance.

CSH. Heterogenous compound symmetry. This structure has non-constant variance and constant correlation.

DIAGONAL. This is a diagonal structure with heterogenous variance. This is the default.

IDENTITY. This is a scaled identity matrix.

SP_POWER. Adapts the first-order autoregressive structure to a time-decaying correlation of unequal-spaced and repeated measurements.

SP_EXPONENTIAL. Assumes that time-decaying correlations decrease exponentially with increasing spatial distances between repeated measurements.

SP_GAUSSIAN. Assumes that time-decaying correlations decrease more rapidly, with increasing spatial distances between repeated measurements, than for the exponential structure.

SP_LINEAR. Assumes that time-decaying correlations decrease linearly with increasing spatial distances between repeated measurements.

SP_LINEARLOG. Assumes that time-decaying correlations decrease linearly with increasing logarithmic spatial distances between repeated measurements.

SP_SPHERICAL. Allows cubic terms of both the correlation function and the spatial distances between repeated measurements.

TOEPLITZ.  

UN_AR1. Specifies the Kronecker product of one unstructured matrix and the other first-order auto-regression covariance matrix. The first unstructured matrix models the multivariate observation, and the second first-order auto-regression covariance structure models the data covariance across time or another factor.

UN_CS. Specifies the Kronecker product of one unstructured matrix and the other compound-symmetry covariance matrix with constant variance and covariance. The first unstructured matrix models the multivariate observation, and the second compound symmetry covariance structure models the data covariance across time or another factor.

UN_UN. Specifies the Kronecker product of two unstructured matrices, with the first one modeling the multivariate observation, and second one modeling the data covariance across time or another factor.

UNSTRUCTURED. This is a completely general covariance matrix.

VARIANCE_COMPONENTS. For repeated measures, the variance components structure is equivalent to the diagonal (DIAGONAL) structure.

SPCOORDS Keyword

The SPCOORDS keyword specifies the variables that define the spatial covariance coordinates. One or more numeric variables must be specified. SPCOORDS is required when SP_POWER, SP_EXPONENTIAL, SP_GAUSSIAN, SP_LINEAR, SP_LINEARLOG, or SP_SPHERICAL is specified for the COVARIANCE_TYPE keyword. It is ignored otherwise.