Parallel groups in bear - CIs [🇷 for BE/BA]

posted by d_labes  – Berlin, Germany, 2010-04-23 11:09 (5895 d 12:37 ago) – Posting: # 5192
Views: 67,987

Dear Old saylor,

❝ In this case, I would be inclined to imagine that the error-sigma2 plus subject-sigma2 would equal the residual error from an anova on lm(lnAUC0t~drug) or something like that.


Full ACK.

To verify this (bear v 2.4.1 parallel group dataset):
'Mixed effects model'
Random effects:
 Formula: ~1 | subj
        (Intercept)  Residual
StdDev:   0.2396947 0.0898856   sqrt(0.2396947^2+ 0.0898856^2)=0.2559941

Fixed effects: lnAUC0t ~ drug
              Value  Std.Error DF  t-value p-value
(Intercept) 7.10189 0.08095245 18 87.72916  0.0000
drug2       0.01594 0.11448405 18  0.13923  0.8908


ElGrandeEM model:
Call:
lm(formula = lnAUC0t ~ drug, data = TotalData)

...

Coefficients:
            Estimate Std. Error t value Pr(>|t|)   
(Intercept)  7.10189    0.08095  87.729   <2e-16 ***
drug2        0.01594    0.11448   0.139     0.89   

Residual standard error: 0.256 on 18 degrees of freedom
Multiple R-squared: 0.001076,   Adjusted R-squared: -0.05442
F-statistic: 0.01939 on 1 and 18 DF,  p-value: 0.8908


Note the totally identical results for the 'drug' effects.

Regards,

Detlew

Complete thread:

UA Flag
Activity
 Admin contact
23,653 posts in 4,991 threads, 1,570 registered users;
106 visitors (0 registered, 106 guests [including 11 identified bots]).
Forum time: 23:47 CEST (Europe/Vienna)

To propose that poor design can be corrected by subtle analysis techniques
is contrary to good scientific thinking.    Stuart J. Pocock

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