Bioequivalence and Bioavailability Forum 12:54 CET

Main page Policy/Terms of Use Abbreviations Latest Posts

 Log in |  Register |  Search

REML or not [Study As­sess­ment]

posted by d_labes - Berlin, Germany, 2016-05-24 16:33  - Posting: # 16360
Views: 12,274

Dear Helmut,

» My preference is REML/Satterthwaite because one could reproduce results in three different software packages.
Emphasis by me.

That's not really a reason. Five SAS implementations are as correct as one ;-).

From a description of Proc MIXED:
"For balanced data the REML method of PROC MIXED provides estimators and hypotheses test results that are identical to ANOVA (OLS method of GLM), provided that the ANOVA estimators of variance components are not negative. The estimators, as in GLM, are unbiased and have minimum variance properties. The ML estimators are biased in that case. In general case of unbalanced data neither the ML nor the REML estimators are unbiased and they do not have to be equal to those obtained from PROC GLM."

The first sentences seem to point to an advantage of REML over ML estimation, left the question of the ddfm aside.

Regards,

Detlew

Complete thread:

Activity
 Mix view
Bioequivalence and Bioavailability Forum |  Admin contact
19,032 posts in 4,059 threads, 1,299 registered users;
online 13 (1 registered, 12 guests [including 9 identified bots]).

When a distinguished but elderly scientist states that
something is possible, he is almost certainly right.
When he states that something is impossible,
he is very probably wrong.    Arthur C. Clarke

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