Bioequivalence and Bioavailability Forum 04:31 CET

Main page Policy/Terms of Use Abbreviations Latest Posts

 Log in |  Register |  Search

Which is better for missing periods PROC GLM or PROC MIXED [RSABE / ABEL]

posted by Mohamed Yehia - Egypt, 2018-01-23 09:48  - Posting: # 18261
Views: 1,651

Hi All,

Hope everything is fine and going well.

For Partial and full replicate studies, if we have some subjects with missing periods, i mean for example subjects who attended only 2 periods in partial replicate

I have only one question:

1) Which method to use following the EMA guidelines; method A "GLM" or method B "Mixed"?.

I am not an expert in statistics, however I read some papers stated "PROC GLM uses least squares or method of moments to fit general linear models. On the other hand, PROC MIXED uses Restricted (or residual) Maximum Likelihood (REML). PROC MIXED is recommended to avoid pitfalls of PROC GLM."

I want a clarified answer please with guideline reference if applicable.

Thanks.

Complete thread:

Activity
 Mix view
Bioequivalence and Bioavailability Forum |  Admin contact
19,037 posts in 4,061 threads, 1,301 registered users;
online 8 (0 registered, 8 guests [including 8 identified bots]).

An expert is a man who has made all the mistakes,
which can be made, in a very narrow field.    Niels Bohr

The BIOEQUIVALENCE / BIOAVAILABILITY FORUM is hosted by
BEBAC Ing. Helmut Schütz
HTML5 RSS Feed