Bioequivalence and Bioavailability Forum

Ahoy!

Rough seas ahead, matey? Read this post first.

❝ […] I am aware that I may be starting a war now.

As I learned from Martin you can only do statistics if you understand the data-generating process. Have we administered three formulations – yes. In how many periods – three. You get the point?

I did some recoding in the past – but only acting in self-defense since I had no confidence-interval based nonparametric method for t_max in my toolbox. Currently my rank order is:

1. Full model: Code everything as it happened in the study. Yes, three treatments in three periods, six sequences. Full stop.
   
2. EMA’s: Bad style. Jury out, verdict pending.
   
3. Recoding: The wonderful thing with the cross-over is that we can forget period-effects (meaning out); what if P1≠P2≠P3 and some responses are shifted from one period to another? Pray for balance!

Tried recoding; too late to send the file to my QAU. Errors possible as usual.

• T1 only
  T1/R: 113.31% [101.57% – 126.41%] CI width 24.84%
CV:   14.86%
GLSM: 6.08 (R), 6.89 (T1)
  
• T2 only
  T2/R: 104.38% [ 89.83% – 121.28%] CI width 31.45%
CV:   20.49%
GLSM: 6.08 (R), 6.35 (T2)

Results for T1 similar to the full model and for T2 to EMA’s. Now what?

Overview

• CIs
             Full model           EMA’s           Recoded 2×2
T1/R   101.35% – 126.67%  103.44% – 124.12%  101.57% – 126.41%
T2/R    93.37% – 116.69%   90.51% – 120.37%   89.83% – 121.28%
  
• CVs
             Full model           EMA’s           Recoded 2×2
T1/R         15.93%             12.23%             14.86%
T2/R          —"—               19.23%             20.49%
  
• GLSMs identical; might not be the case if imbalanced! Detlew assumed that already a while ago.

Dropped subject 12:

• CIs
             Full model           EMA’s           Recoded 2×2
T1/R    97.76% – 122.45%  101.22% – 119.59%   99.14% – 120.26%
T2/R    90.43% – 113.27%   87.31% – 115.02%   86.63% – 115.34%
  
• CVs
             Full model           EMA’s           Recoded 2×2
T1/R         15.25              10.44%             12.35%
T2/R          —"—               17.35%             18.38%
  
• GLSMs
             Full model           EMA’s           Recoded 2×2
R             6.20                NA                 NA
T1            6.78                NA                 NA
T2            6.27                NA                 NA
R                                6.19               6.28
T1                               6.81               6.85
R                                6.21               6.23
T2                               6.22               6.22

As expected we get different GLSMs for the separated evaluations in EMA’s method and after recoding. But since the data are not presented…

Ignorance is bliss.

Smooth sailin’, an’ fair winds t’ ye!