Fixed effects model: changing the F, p values [Two-Stage / GS Designs]

posted by zizou – Plzeň, Czech Republic, 2016-10-11 01:06 (1396 d 15:55 ago) – Posting: # 16713
Views: 29,032

Dear mittyri,
for the results consistency (R versus Phoenix as you reported), there should be one more term of marvelous effect x) ... you posted it as number 7: (I resorted it for comparison of F and p values, note: int and Trt are missing in the results from R code)
»   Dependent Hypothesis Numer_DF Denom_DF        F_stat     P_value
» 5   Ln(Var)  Group*Per        2       14 3.2110481e+00 0.071153125
» 7   Ln(Var)  Trt*Group        1       14 2.3942317e-01 0.632200219
» 2   Ln(Var)      Group        1       14 9.9615453e-01 0.335181899
» 3   Ln(Var)        Seq        1       14 9.7094813e-01 0.341167964
» 4   Ln(Var)  Group*Seq        1       14 5.7364354e-02 0.814182229
» 1   Ln(Var)        int        1       14 3.1047428e+03 0.000000000
» 6   Ln(Var)        Trt        1       14 3.4404496e+00 0.084798088


If you change the muddle:
muddle <- lm(log(Var)~Group+Seq+Seq*Group+Subj%in%(Seq)+Per%in%Group+Trt+Group*Trt, data=data)
and run the mentioned code... Voilà!
Type III sum of squares:
(mimicing SAS/SPSS but with Seq tested against Subj)

log(Var) ~ Group + Seq + Seq * Group + Subj %in% (Seq * Group) + ...
               Df  Sum Sq   Mean Sq  F value     Pr(>F)   
Group:Per       2 0.04514 0.0225681  3.21105   0.071153 . 
Group:Trt       1 0.00168 0.0016827  0.23942   0.632200   
Group           1 0.22546 0.2254640  0.79946   0.386368   
Seq             1 0.27383 0.2738263  0.97095   0.341168   
Group:Seq       1 0.01618 0.0161779  0.05736   0.814182   
Group:Seq:Subj 14 3.94827 0.2820195 40.12641 7.5802e-09 ***
Residuals      14 0.09840 0.0070283                       
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

The comparison is telling us that with groups it will be little bit more complicated.

» Now Group factor seems to be more suitable.
» What bothers me is that Group effect is not equal in R and PHX, cannot figure out the reason
Good luck!
zizou

Complete thread:

Activity
 Admin contact
20,977 posts in 4,374 threads, 1,460 registered users;
online 31 (2 registered, 29 guests [including 20 identified bots]).
Forum time: Friday 17:01 CEST (Europe/Vienna)

When someone says his conclusions are objective,
he means that they are based on prejudices
which many other people share.    Celia Green

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