MSimoes
Junior

Portugal,
2019-01-07 12:13

Posting: # 19741
Views: 694
 

 Bootstrap f2 - which software? [Software]

Dear BEBAC team,

Now that the MSD is dead and bootstrap f2 finally king :-), I would like your opinion on a good (and free) software for trustable calculation of bootstrap f2.

I have been using DDSolver, but recently I heard that the Spanish agency replied to a dossier submission saying that it is not acceptable because of miscalculations. We are now moving to Ph-Eq software, as I have seen some posts here in the BEBAC forum. What is your opinion on these softwares, do you know why the DDSolver is not recommended? What about Ph-Eq, any feedback? It is not so user-friendly as the DDSolver, that was my first impression.

I am a pharmacist, not expert in statistics or maths :-) It is very difficult sometimes to discriminate the adequacy between tools... I would appreciate your kind support :-)

Thanks to you all,
And a Happy New Year!

Regards,
MSimoes
Shuanghe
Regular

Spain,
2019-01-07 13:15

@ MSimoes
Posting: # 19742
Views: 615
 

 Bootstrap f2 - which software?

Dear MSimoes,

» I have been using DDSolver, but recently I heard that the Spanish agency replied to a dossier submission saying that it is not acceptable because of miscalculations.

From the information I got from one meeting with the agency, they use R that was developed by a professor in certain university. I suggested that they should publish the code with the seed number so everyone can use and reproducibility wouldn't be an issue. Haven't seen any thing published yet.

» do you know why the DDSolver is not recommended?

I've never used DDSolver's calculation for f2 or bootstrapped f2 for regulatory submission. I have no idea how internal code of DDSolver works but from the f2 calculation I saw, it seems that the code doesn't evaluate if your number of points is valid according to EU or US guidance (By that I mean to say the CV% of early points, how many points > 85% release etc). the results of f2 depends on how you select the points. If bootstrapped f2 also works similarly, then I wouldn't be surprised if the agency refuse to accept it.


» What about Ph-Eq, any feedback?

Well, the result of this program is not reproducible. You'll find Helmut's about this in this forum. however, some articles were published using this program and one of the authors is from Spanish agency, so I guess that you can try it. :-D

All the best,
Shuanghe
MSimoes
Junior

Portugal,
2019-01-07 16:32

@ Shuanghe
Posting: # 19747
Views: 604
 

 Bootstrap f2 - which software?

Dear Shuanghe,

Thanks for your feedback!

» From the information I got from one meeting with the agency, they use R that was developed by a professor in certain university. I suggested that they should publish the code with the seed number so everyone can use and reproducibility wouldn't be an issue. Haven't seen any thing published yet.

Very good idea!

» Well, the result of this program is not reproducible. You'll find Helmut's about this in this forum. however, some articles were published using this program and one of the authors is from Spanish agency, so I guess that you can try it. :-D

Yes, I saw it, thanks! ... Well, what are the options to do it right? No programming involved, please :-D I also have JMP software, from SAS.

Once again, thanks for your help.

Regards,
MSimoes
ElMaestro
Hero

Denmark,
2019-01-07 16:39

@ MSimoes
Posting: # 19748
Views: 592
 

 Bootstrap f2 - which software?

Hi,

» Yes, I saw it, thanks! ... Well, what are the options to do it right? No programming involved, please :-D I also have JMP software, from SAS.

if it is just a single dataset or two then send it (/them) here. Use the forum's email option. I will send you the result by email.

if (3) 4

x=c("Foo", "Bar")
b=data.frame(x)
typeof(b[,1]) ##aha, integer?
b[,1]+1 ##then let me add 1



Best regards,
ElMaestro

"(...) targeted cancer therapies will benefit fewer than 2 percent of the cancer patients they’re aimed at. That reality is often lost on consumers, who are being fed a steady diet of winning anecdotes about miracle cures." New York Times (ed.), June 9, 2018.
MSimoes
Junior

Portugal,
2019-01-07 17:58

@ MSimoes
Posting: # 19753
Views: 571
 

 Bootstrap f2 - which software?

Thanks everyone for your help!

I've read about the bootf2BCA in this forum, it seems to create huge files! It seems we still need an optimized tool, despite all the good progress so far.

I will also try this one, at least there is no warning of lack of reproducibility (so far). And I will be alert to any news on this.

Thanks!

Regards,
MSimoes
yjlee168
Senior
avatar
Homepage
Kaohsiung, Taiwan,
2019-01-07 17:07

@ Shuanghe
Posting: # 19750
Views: 591
 

 bootf2BCA & PhEq_Bootstrap

Hi

» From the information I got from one meeting with the agency, they use R that was developed by a professor in certain university.

bootf2BCA? if yes, it can be downloaded from SourceForge. Detlew is the first one to report this package in this Forum, as far as I can remember. In addition, Poland is the country that the developer comes from. He is also the developer of PhEq_bootstrap.

#############################################################
bootf2BCA v1.1
Author: Aleksander Mendyk
Chair of Pharmaceutical Technology and Biopharmaceutics
Faculty of Pharmacy
Jagiellonian University-Medical College
Medyczna 9 St
30-688 Kraków, Poland
phone: +48-12-6205-604
e-mail: mfmendyk@cyf-kr.edu.pl, aleksander.mendyk@uj.edu.pl
############################################################

All the best,
---Yung-jin Lee
bear v2.8.3-3:- created by Hsin-ya Lee & Yung-jin Lee
Kaohsiung, Taiwan http://pkpd.kmu.edu.tw/bear
Download link (updated) -> here
Shuanghe
Regular

Spain,
2019-01-07 17:22

@ yjlee168
Posting: # 19752
Views: 583
 

 bootf2BCA & PhEq_Bootstrap

Hi Yung-jin,

» bootf2BCA? if yes, it can be downloaded from SourceForge. Detlew is the first one to report this package in this Forum, as far as I can remember. In addition, Poland is the country that the developer comes from. He is also the developer of PhEq_bootstrap.

Thanks. I almost forgot this. I saw Detlew's post some time ago. I don't know if this is the one the agency meant. I had the impression that the professor is working in certain university in Spain, but again, I'm not sure since the name was never mentioned in the meeting.

In any case, now we have an additional option to try. :-D

All the best,
Shuanghe
Activity
 Thread view
Bioequivalence and Bioavailability Forum |  Admin contact
19,271 posts in 4,099 threads, 1,315 registered users;
online 17 (0 registered, 17 guests [including 11 identified bots]).

It’s easy to lie with statistics;
it is easier to lie without them.    Frederick Mosteller

The BIOEQUIVALENCE / BIOAVAILABILITY FORUM is hosted by
BEBAC Ing. Helmut Schütz
HTML5