Scaling of Cmin [Regulatives / Guidelines]

posted by VStus – Poland, 2017-02-03 16:37 (2934 d 17:49 ago) – Posting: # 17008
Views: 12,030

Dear zizou,

Thank you very much for the feedback!

I've tried 4 periods instead of 2 and got even higher variation, which seems to be an overestimation:
summary(data)
##       subj    seq     prd    drug   rep          AUC       
##  1      : 2   RT:20   1:10   R:40   R1:20   Min.   : 439.0 
##  2      : 2   TR:20   2:10          R2:20   1st Qu.: 656.5 
##  3      : 2           3:10                  Median : 781.5 
##  4      : 2           4:10                  Mean   : 795.6 
##  5      : 2                                 3rd Qu.: 929.8 
##  6      : 2                                 Max.   :1297.0 
##  (Other):28
anovadata <- lm(log(AUC) ~ seq + subj:seq + rep + prd, data=data, na.action=na.exclude)
anova(anovadata)
## Analysis of Variance Table
##
## Response: log(AUC)
##           Df  Sum Sq  Mean Sq F value  Pr(>F) 
## seq        1 0.20989 0.209885  6.2514 0.02230 *
## rep        1 0.00507 0.005067  0.1509 0.70222 
## prd        1 0.00169 0.001689  0.0503 0.82505 
## seq:subj  18 1.55131 0.086184  2.5670 0.02631 *
## Residuals 18 0.60433 0.033574                 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
100*sqrt(exp(0.033574)-1)
## [1] 18.47812


Removing replication from the model does not change residual MS :)

Regards, VStus

Complete thread:

UA Flag
Activity
 Admin contact
23,381 posts in 4,914 threads, 1,662 registered users;
31 visitors (0 registered, 31 guests [including 10 identified bots]).
Forum time: 10:27 CET (Europe/Vienna)

Science is built up with facts, as a house is with stones.
But a collection of facts is no more a science
than a heap of stones is a house.    Henri Poincaré

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