Stats for GLM pairwise comparisons

[Kam T]

Dear SPSS users,
Why is there no obvious way to obtain the test statistic for pairwise
comparison in the SPSS GLMs. Specifically I am using SPSS v.16 running RM
(5x5)ANOVA for the main effect terms I get my EM difference contrasts
between all factor levels, which is nice, but there is no test statistic of
comparison(s). Why not? and How can I get it? Furthermore, for the
interaction term in my case I get only the cell means but no comparisons
between the means. What is that about?
I already know about the WS contrasts table. But that is not what I am
looking for here!
Thanks in advance
Kam

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Bruce Weaver]

K T-4 wrote

Dear SPSS users,
Why is there no obvious way to obtain the test statistic for pairwise
comparison in the SPSS GLMs. Specifically I am using SPSS v.16 running RM
(5x5)ANOVA for the main effect terms I get my EM difference contrasts
between all factor levels, which is nice, but there is no test statistic of
comparison(s). Why not? and How can I get it? Furthermore, for the
interaction term in my case I get only the cell means but no comparisons
between the means. What is that about?
I already know about the WS contrasts table. But that is not what I am
looking for here!
Thanks in advance
Kam

Have you tried the COMPARE option on an EMMEANS subcommand?  Here's a modified example from the Help files.

GLM DEP BY A B
  /EMMEANS = TABLES(A*B) COMPARE(A)
  /DESIGN.

* The output of this analysis includes a pairwise comparisons table for the dependent variable DEP.

* Assume that A has three levels and B has two levels. The first level of A is compared with the second and third levels, the second level is compared with the first and third levels, and the third level is compared with the first and second levels. These pairwise comparisons are done at each level of B.

Here's some more info from the Help.

COMPARE(factor) ADJ(method) 

Main-effects or simple-main-effects omnibus tests and pairwise comparisons of the dependent variable. This option gives the mean difference, standard error, significance, and confidence interval for each pair of levels for the effect that is specified in the TABLES command, as well as an omnibus test for that effect. If only one factor is specified on TABLES, COMPARE can be specified by itself; otherwise, the factor specification is required. In this case, levels of the specified factor are compared with each other for each level of the other factors in the interaction.  

  The optional ADJ keyword allows you to apply an adjustment to the confidence intervals and significance values to account for multiple comparisons. Available methods are LSD (no adjustment), BONFERRONI, or SIDAK.  

  If OVERALL is specified on TABLES, COMPARE is invalid.