Calculation of SE Geometric LSM [General Sta­tis­tics]

posted by randombadger – UK, 2011-06-29 18:20 (5475 d 02:40 ago) – Posting: # 7195
Views: 4,824

Hi all,

I'd like to calculate the SE of the Geometric LSM however my colleague and I disagree on which formula is correct!

Based on the logged data, we have the LSMean & SE from the Mixed Model.
In the past I've calculated SE Geom LSM = EXP(LSMean) * SE (based on former colleague's recommendations) whereas my colleague suggests simply exponentiating SE.

Any thoughts? Does anyone have a reference?

Thanks,
RB

Complete thread:

UA Flag
Activity
 Admin contact
23,655 posts in 4,993 threads, 1,571 registered users;
172 visitors (0 registered, 172 guests [including 33 identified bots]).
Forum time: 21:00 CEST (Europe/Vienna)

The great tragedy of Science – the slaying
of a beautiful hypothesis by an ugly fact.    Thomas Henry Huxley

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5