Vienna, Austria,
2021-04-08 19:09
(1104 d 22:30 ago)

Posting: # 22305
Views: 26,087

 Requesting data for a publication 📥 ♻️ 🚀 [General Sta­tis­tics]

Dear all,

we are collecting data for a publication about the annoying ‘Group-by-Treatment interaction’ (for some thoughts see this article).
Below what we have so far in a meta-analysis of multi-group studies:


To make a long story short: As expected, significant Group-by-Treatment interactions were detected at approximately the level of the test (0.05) and below the upper 95% significance limit of the binomial test. Hence, based on our observations in well-controlled studies likely they are mere ‘statistical artifacts’, i.e., false positives. The Kol­mo­go­rov–Smirnov tests were not significant, accepting the expected standard uniform distribution of \(\small{p(G\times T)}\).
At a recent BE workshop1 I had a conversation with a prominent member of the FDA. She told that the agency tests the Group-by-Treat­ment interaction at the 0.05 level, thus reducing the false positive rate observed at the previously used 0.1 level. But then she also said

»We often see not only p-values just below 0.05, but also some with 0.001…«

It’s a common fallacy to regard the p-value as the probability that the null hypothesis is true (or the alternative hypothesis is false).2 The outcome of a level \(\small{\alpha}\)-test is dichotomous: Hypotheses are considered true or false, not something that can be represented with a probability.

Any type of comparative BA study (BE, food-effect, DDI, dose-proportionality) is welcome.
Of course,  data will be treated strictly confidential and not published . The preferred data format is CSV (though xls(x), ODS, SAS XPT or Phoenix project files would serve as well).

Columns (any order is fine):
  1. Company or individual (text)
  2. Study code (text)
  3. Analyte (text) if you don’t want to give this information, use not spec. X, where X is an integer 1 … number of analytes
  4. Design (2x2x2, 3x6x3, 3x3, 4x4, 2x2x4, 2x2x3, 2x3x3)
    Simple crossover, 6-sequence 3-period Williams’ design, 3-period Latin Squares, 4-sequence 4-period Williams’ design or 4-period Latin Squares, 2-sequence 4-period full replicate, 2-sequence 3-period full replicate, partial replicate; no parallel design
  5. Drug (integer) 1 … number of analytes
  6. Subject (integer or text) min(n) … max(n); missings due to dropouts not a problem
  7. Group or Site (integer) 1 … number of groups / sites
  8. Sequence (character or integer), e.g., TR, RT or AB, BA or 1, 2 (simple crossover), e.g., TRTR, RTRT or TRT, RTR (full re­pli­cate designs), TRR, RTR, RRR (partial re­pli­cate design), ABC, BCA, CAB (Latin Squares), ABC, ACB, BAC, BCA, CAB, CBA (Williams’ design)
    Essentially any kind of coding is possible, as long as it is unambiguous.
  9. Treatment (character) mandatory T or R (not A or B)
  10. Period (integer) 1 … number of periods
  11. AUC (numeric); for single dose AUC0–t or AUC0–72, for multiple dose AUC0–τ.
    Missing values should be coded with NA (preferred) or Missing.
  12. Cmax (numeric)
Optional columns:
  • Interval (integer) days separating groups; only if equal across groups
  • Sex (character) f or m
If you want to participate, please send data to [email protected].
No cherry-picking, otherwise we will fall into the trap of selection bias and the outcome will be useless. Hence, if you decide to provide data, please do so irrespective of whether you ‘detected’ a significant Group-by-Treatment interaction or not.
We are primarily working on 2×2×2 crossover designs. How­ever, if you have data of replicate designs, fine as well. In Higher-Order crossover designs indicate which of the treatments is the test and the reference.
If possible, give the analyte. Once we have enough data sets, we will perform sub-group analyses.

So far we have only data of one multi-site study. If you could share some data, great.

THX in advance!

  1. Medicines for Europe. 2nd Bioequivalence Workshop. Session 2 – ICH M13 – Bioequivalence for IR solid oral dosage forms. Brussels. 26 April 2023.
  2. Wasserstein RL, Lazar NA. The ASA’s Statement on p-Values: Context, Process, and Purpose. Am Stat. 2016; 70(2): 129–33. doi:10.1080/00031305.2016.1154108.

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Vienna, Austria,
2023-02-23 11:46
(419 d 04:53 ago)

@ Helmut
Posting: # 23775
Views: 9,474

 Requesting data for another publication

Dear all,

I’m also collecting data to assess a ‘Sex-by-Formulation interaction’ because in Section 2.1.1 of ICH M13A we find:

Subjects should be at least 18 years of age and preferably have a Body Mass Index between 18.5 and 30.0 kg/m2. If a drug product is intended for use in both sexes, it is recommended the study include male and female subjects. […] Subjects should preferably be non-nicotine users.

Obviously there are no concerns about extrapolating results to patients < 18 years, to obese patients (in the US a whopping 42% of the adult population), or to 23% of adults smoking tobacco. However, this sentence is similar to what the FDA recently recommended but is not stated in any other of the global guidelines. Where does this come from and why? Science or rather (gender)politics?1,2 We have only few anecdotal reports and small meta studies with contradicting results. Nevertheless, authors of the largest one concluded:3

There is no evidence to require studies in both sex groups, combined or separately.

In the past – at least in Europe – the majority of studies were performed in males only. We know that pharmacovigilance is not very sen­sitive. However, in 23.8 million drug switches in The Netherlands only 1,348 ADRs were reported (i.e., in 0.006% of switches)…4

Recently I gave presentations on the topic.5,6 In the meantime I have more data (228 mixed-sex datasets, 190 passing BE for AUC; 3,970 males, 3,302 females):



  • Similar within-subject CV in males (x̃ 18.68%) and females (x̃ 17.12%). Therefore, I could not confirm the hearsay of CVw being larger in females than in males.
  • No evidence that medians of Point Estimates of subgroups differ (notches of box plots overlap).
  • Difference in PEs of males and females > ±20% in 3.16% of datasets.
  • Difference in PEs of males and females ≤ ±10% in 78.4% of datasets.
  • p(S × F) uniformly distributed (Kol­mo­go­rov–Smirnov p 0.8823).
  • Significant (p < 0.1) S × F interaction in 11.6% of datasets; below the upper 95% significance limit of the binomial test (0.1433).
    Some authors discussed an even higher significance limit of 0.2 (being aware of the increased false positive rate).7 What do we observe here? 19.5% (<0.2538)…
  • Discordant Qualitative Interaction8 in 1.58% of datasets.
I had only limited information about the subjects’ bodyweight. However, if the AUC was adjusted by bodyweight, the apparent difference between sexes mainly disappeared.


  1. Criado Perez C. Invisible Women: Exposing data bias in a world designed for men. New York: Random House; 2019.
  2. Senn S. Randomisation Versus Random Sampling: Clinical Trials and the Representation Fallacy. Presentation at the Center for Me­di­cal Data Science of the Medical University of Vienna. 20 October 2023.
  3. González-Rojano E, Marcotegui J, Ochoa D, Román M, Álvarez C, Gordon J, Abad-Santos F, García-Arieta A. Investigation on the Existence of Sex-By-Formulation Interaction in Bioequivalence Trials. Clin Pharm Ther. 2019; 106(5): 1099–112. doi:10.1002/cpt.1539.
  4. Glerum PJ, Neef C, Burger DM, Yu Y, Maliepaard M. Pharmacokinetics and Generic Drug Switching: A Regulator’s View. Clin Phar­ma­co­kin. 2020; 59: 1065–9. doi:10.1007/s40262-020-00909-8.
  5. Schütz H. Statistical challenges and opportunities in ICH M13A. Presentation at: 2nd Bioequivalence Workshop, Brussels. 26 April 2023. Online.
  6. Schütz H. Sex– and group–related problems in BE. A delusion. Presentation at: BioBridges, Prague. 21 September 2023. Online.
  7. Alosh M, Fritsch K, Huque M, Mahjoob K, Pennello G, Rothmann M, Russek-Chen E, Smith E, Wilson S, Yiu L. Sta­tis­tical Con­si­de­ra­tions on Subgroup Analysis in Clinical Trials. Stat Pharm Res. 2015; 7(4): 286–304. doi:10.1080/19466315.2015.1077726.
  8. Sun W, Schuirmann D, Grosser S. Qualitative versus Quantitative Treatment-by-Subgroup Interaction in Equivalence Studies with Mul­tiple Subgroups. Stat Pharm Res. 2023; 15(4): 737–47. doi:10.1080/19466315.2022.2123385.

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
UA Flag
 Admin contact
22,985 posts in 4,823 threads, 1,653 registered users;
40 visitors (0 registered, 40 guests [including 2 identified bots]).
Forum time: 17:39 CEST (Europe/Vienna)

Complex, statistically improbable things are by their nature
more difficult to explain than
simple, statistically probable things.    Richard Dawkins

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