Extra-reference or partial replicate design [Software]
Dear all,
FYI:
The 3-sequence-3-period replicate design with the sequences
[1] R.J. McNally
Tests for Individual and Population Bioequivalence Using 3-Period Crossover Designs
and the 2-sequence variant using only the two first sequences in
[2] S.-C. Chow, J. Shao and H. Wang
Individual bioequivalence testing under 2×3 designs
Statist. Med. 2002; 21:629–648
which can be found [1] here and [2] there.
These papers deal with individual BE but the parts relevant for average BE can easily extracted.
Interesting enough these papers state, that the intra-individual variance component for T(est) is not identifiable/estimable, due to the "partial" replicate nature of these designs (replicates only for R).
Thus one would expect some difficulties with the FDA SAS code, which has a covariance parameter for that in the model. But my little experimentation with it and some artificial data for an extra-reference design show that the code is able to deliver a value for that variance parameter sWT.
Black magic
or some sort of perpetuum mobile of information?
Because the intra-individual variance for the Reference is identifiable (regardless which method, REML or method of moments) one could go with Reference scaled ABE as described in
Haidar et al.
Evaluation of a scaling approach for the bioequivalence of highly variable drugs
AAPS J. 2008 Sep;10(3):450-4. Epub 2008 Aug 26
FYI:
The 3-sequence-3-period replicate design with the sequences
TRR
RTR
RRT
[1] R.J. McNally
Tests for Individual and Population Bioequivalence Using 3-Period Crossover Designs
and the 2-sequence variant using only the two first sequences in
[2] S.-C. Chow, J. Shao and H. Wang
Individual bioequivalence testing under 2×3 designs
Statist. Med. 2002; 21:629–648
which can be found [1] here and [2] there.
These papers deal with individual BE but the parts relevant for average BE can easily extracted.
Interesting enough these papers state, that the intra-individual variance component for T(est) is not identifiable/estimable, due to the "partial" replicate nature of these designs (replicates only for R).
Thus one would expect some difficulties with the FDA SAS code, which has a covariance parameter for that in the model. But my little experimentation with it and some artificial data for an extra-reference design show that the code is able to deliver a value for that variance parameter sWT.
Black magic

Because the intra-individual variance for the Reference is identifiable (regardless which method, REML or method of moments) one could go with Reference scaled ABE as described in
Haidar et al.
Evaluation of a scaling approach for the bioequivalence of highly variable drugs
AAPS J. 2008 Sep;10(3):450-4. Epub 2008 Aug 26
—
Regards,
Detlew
Regards,
Detlew
Complete thread:
- SAS code of partial replicate design pa1kumar.anna 2008-12-01 09:51 [Software]
- Etiquette Ohlbe 2008-12-01 10:45
- SAS code for what? d_labes 2008-12-02 09:17
- partial replicate = 3-period replicate Helmut 2008-12-03 15:42
- partial replicate = 3-period replicate MGR 2008-12-04 11:19
- 3-period replicate designs and SAS d_labes 2008-12-04 14:17
- Extra-reference or partial replicate designd_labes 2008-12-12 10:51
- Extra-reference or partial replicate design Helmut 2008-12-12 11:34
- Simple minded d_labes 2008-12-12 13:28
- Simple minded Helmut 2008-12-12 14:58
- SAS and WinNonlin d_labes 2008-12-12 15:44
- SAS and WinNonlin Helmut 2008-12-12 16:33
- SAS and WinNonlin BEQool 2024-07-29 09:38
- Phoenix RSABE-template Helmut 2024-07-29 13:29
- Phoenix RSABE-template BEQool 2024-07-29 19:47
- CVw in Phoenix RSABE-template Helmut 2024-07-30 09:15
- CVw in Phoenix RSABE-template BEQool 2024-07-30 10:56
- CVw in Phoenix RSABE-template and PowerTOST CI2CV() Helmut 2024-07-30 11:23
- CVw in Phoenix RSABE-template and PowerTOST CI2CV() BEQool 2024-07-31 05:49
- General ABE? mittyri 2024-07-31 18:25
- General ABE? BEQool 2024-08-01 05:45
- General ABE? mittyri 2024-07-31 18:25
- CVw in Phoenix RSABE-template and PowerTOST CI2CV() BEQool 2024-07-31 05:49
- CVw in Phoenix RSABE-template and PowerTOST CI2CV() Helmut 2024-07-30 11:23
- CVw in Phoenix RSABE-template BEQool 2024-07-30 10:56
- CVw in Phoenix RSABE-template Helmut 2024-07-30 09:15
- Phoenix RSABE-template BEQool 2024-07-29 19:47
- Phoenix RSABE-template Helmut 2024-07-29 13:29
- SAS and WinNonlin BEQool 2024-07-29 09:38
- SAS and WinNonlin Helmut 2008-12-12 16:33
- Switchability and Prescribability in WinNonlin MGR 2008-12-30 10:12
- PBE and IBE in WinNonlin Helmut 2008-12-30 16:04
- PBE and IBE in WinNonlin MGR 2008-12-31 07:52
- Switchability NPavan 2009-01-12 13:10
- PBE and IBE in WinNonlin MGR 2008-12-31 07:52
- PBE and IBE in WinNonlin Helmut 2008-12-30 16:04
- SAS and WinNonlin d_labes 2008-12-12 15:44
- Simple minded Helmut 2008-12-12 14:58
- Simple minded d_labes 2008-12-12 13:28
- Extra-reference or partial replicate design Helmut 2008-12-12 11:34
- Extra-reference or partial replicate designd_labes 2008-12-12 10:51
- partial replicate = 3-period replicate Helmut 2008-12-03 15:42