EMMEANS Subcommand (GENLINMIXED command)

The EMMEANS subcommand displays estimated marginal means of the target for all level combinations of a set of factors. Note that these are predicted, not observed, means. Estimated marginal means can be computed based on the original scale of the target or the based on the link function transformation.

  • Multiple EMMEANS subcommands are allowed. Each is treated independently.
  • The EMMEANS subcommand can be specified with no additional keywords. The output for an empty EMMEANS subcommand is the overall estimated marginal mean of the response, collapsing over any factors.
  • Estimated marginal means are not available if the multinomial distribution is used. If DISTRIBUTION = MULTINOMIAL on the MODEL subcommand and the EMMEANS subcommand is specified, then EMMEANS is ignored and a warning is issued.

The TABLES keyword specifies the cells for which estimated marginal means are displayed.

  • Valid options are all-factor effects appearing on the EFFECTS keyword of the FIXED subcommand, including main effects factors such as a b, all-factor interactions such as a*b, and all-factor nested effects such as a(b), if a and b are factors.
  • If the TABLES keyword is specified, then the procedure collapses over any other factors specified on the command but not on the TABLES keyword before computing the estimated marginal means for the target.
  • If the TABLES keyword is not specified, then the overall estimated marginal mean of the target, collapsing over any factors, is computed.

Examples

GENLINMIXED
  /FIXED EFFECTS=a b
  /EMMEANS TABLES=a*b.

GENLINMIXED
  /FIXED EFFECTS=a*b
  /EMMEANS TABLES=a
  /EMMEANS TABLES=b.

GENLINMIXED
  /FIXED EFFECTS=a b a*b
  /EMMEANS TABLES=a
  /EMMEANS TABLES=b
  /EMMEANS TABLES=a*b.
  • The first two commands fail because the effects listed on the TABLES keywords are not listed on the EFFECTS keyword. The third command succeeds.

COMPARE Keyword

The COMPARE keyword specifies a factor, the levels of which are compared using the contrast type specified on the CONTRAST keyword.

  • Valid options are factors appearing on the TABLES keyword.
  • The COMPARE keyword is valid only if the TABLES and CONTRAST keyword is also specified.
  • By default, the procedure sorts levels of the factors in ascending order and defines the highest level as the last level. (If the factor is a string variable, then the value of the highest level is locale-dependent.) However, the sort order can be modified using the INPUTS_SORT_ORDER keyword on the BUILD_OPTIONS subcommand.

CONTRAST Keyword

The CONTRAST keyword specifies the type of contrast to use for the levels of the factor on the COMPARE keyword. The CONTRAST keyword creates an L matrix (that is, a coefficient matrix) such that the columns corresponding to the factor match the contrast given. The other columns are adjusted so that the L matrix is estimable.

  • The CONTRAST keyword is valid only if the COMPARE keyword is also specified.
  • If the COMPARE keyword is specified without CONTRAST, then pairwise comparisons are performed for the factor on COMPARE.
  • SIMPLE contrasts are defined with respect to the last level as determined by the INPUTS_CATEGORY_ORDER specification on the BUILD_OPTIONS subcommand.

The following contrast types are available.

NONE. No comparisons. This is the default.

PAIRWISE. Pairwise comparisons are computed for all levels of the specified or factor. Pairwise contrasts are not orthogonal.

DEVIATION. Each level of the factor is compared to the grand mean. Deviation contrasts are not orthogonal.

SIMPLE. Each level of the factor except the last is compared to the last level. Simple contrasts are not orthogonal.