ANOVA Partial SS sheet for full replicate EMA Method B

Phoenix Certara Forums Phoenix WNL basics
1

Dear All,

Could you please help me with producing the conventional Partial SS sheet for Full replicate data set with Method B?

I run the template “EMA ABEL Full Replicate” from here and reviewed the output sheets of ‘BE Method B log’ object. If I do not execute it in PHX6.4, I see the sheet named 'Partial Tests" (so it was executed only in PHX6.3 by Ana Henry) with desired output.

But when I run this object in PHX 6.4, Partial SS disappears and I see only Partial Tests.

Are there any workarounds?

If I cannot get this sheet, how to calculate the values for this table?

2

Hi Mitty, in version 6.4 we cleaned up some of the BE, output, please see the release notes (page 6 WinNonlin) for full details;

Issues Corrected : Bioequivalence

…

SS and MS are now included in the output only under appropriate circumstances (QC 12608, 13275): If a user had replicated data but changed the Bioequivalence model to the default non-replicated crossover model, SS and MS output were incorrectly generated. This also occurred if a Repeated model was added to the default non-replicated crossover model.

Simon

Phoenix WinNonlin 6.4 Release Notes.pdf (567 KB)

3

Hi Simon,

Thanks for quick reply!

could you please enlighten me - what is the reason to exclude the SS tables? Did Phoenix produce wrong values?

I’ve found it unconvenient, because some protocols state that these tables should be included.

What about workaround? Do you know how to produce SS tables from other sheets in result?

Miity

4

Hi Simon,

I think I understand now the logic.

The PROC MIXED procedure does not have SS table.

The reason is:

PROC MIXED does not produce an analysis of variance table, because it uses estimation methods based on different principles.