joy_fm ☆ Indonesia, 2014-11-03 09:19 (3454 d 18:37 ago) Posting: # 13822 Views: 7,181 |
|
Dear all, Would you mind to answer my question related to Bioequivalence Statistical Analysis ? Which one is the correct one for SE Difference ? a. SE Difference = (MS residual x (1/nTR + 1/nRT)1/2 or b. SE Difference = (MS residual x (2/n)1/2 Note : n = subject number of Bioequivalence study nRT = subject number who get Reference Drug in Period 1, and get Test Drug in Period 2 = 1/2 n nTR = subject number who get Test Drug in Period 1, and get Reference Drug in Period 2 = 1/2 n If I calculate 2 formula from a and b, the results will be different. a. SE Difference = (MS residual x (1/nTR+ 1/nRT)1/2 = (MS residual x (1/(1/2n)+ (1/(1/2n)1/2 = (MS residual x (2/n + 2/n)1/2 = (MS residual x (4/n)1/2 b. SE Difference = (MS residual x (2/n)1/2 Would you mind to share the guideline for SE Difference calculation ? Thank you Best Regards joy_fm |
Mahmoud ★ Jordan, 2014-11-06 21:33 (3451 d 06:23 ago) @ joy_fm Posting: # 13834 Views: 6,214 |
|
Dear Sir 1.SE Difference = (MS residual/2 x (1/nTR + 1/nRT)1/2 if nRT is not equal nTR 2.SE Difference = (MS residual x (2/n)1/2 if nRT = nTR=n/2 n = subject number of Bioequivalence study Dr.Mahmoud Abdel Mohsen Amman-Jordan statistiain Edit: You forgot closing brackets. Your formulas should read:
|
joy_fm ☆ Indonesia, 2014-11-07 05:05 (3450 d 22:51 ago) @ Mahmoud Posting: # 13836 Views: 6,031 |
|
Dear Dr. Mahmoud Abdel Mohsen, Thank you for answering my question. Would you mind to share the guideline ? Because I just have Canada Guideline "Guidance Document Conduct and Analysis of Comparative Bioavailability Studies" effective date May 22, 2012, that state: SEDifference = (2MSResidual/n)0.5 Thank you Best regards Ms. Joy_fm |
Mahmoud ★ Jordan, 2014-11-07 06:42 (3450 d 21:14 ago) @ joy_fm Posting: # 13837 Views: 6,016 |
|
Dear sir No if you need any information i can send to you Didn’t you realize? Ms. Joy = Madam ≠ Sir… Thankfully the BEBA Forum is not a boys-only club. [Helmut] |
Helmut ★★★ Vienna, Austria, 2014-11-07 15:29 (3450 d 12:27 ago) @ joy_fm Posting: # 13840 Views: 6,020 |
|
Hi Joy, ❝ Would you mind to share the guideline ? It is not a particular good idea to rely on guidelines – especially when it comes to statistics. ❝ Because I just have Canada Guideline […] ❝ SEDifference = (2MSResidual/n)0.5 Not the sole error in Health Canada’s guidance; the formula – as Mahmoud wrote – is only correct in the balanced case. Always use $$SE=\sqrt{\frac{MSE}{2}\left(\frac{1}{n_\textrm{TR}}+\frac{1}{n_\textrm{RT}}\right)}\tag{1}$$ HC’s example dataset is balanced only by chance (one dropout in each sequence) and imbalanced studies are not uncommon in BE. BTW, it took HC 21 (‼) years to give the correct formula for the intra-subject CV: $$CV_\textrm{intra}=\sqrt{\exp(MSE)-1}\tag{2}$$ In HC’s first (1991) guidance – and still in the 2009 (!) draft – the wrong $$CV_\textrm{intra}=\sqrt{MSE}\tag{3}$$ was given. For AUCT of the example data set one gets 0.275 by \(\small{(2)}\) and 0.270 by \(\small{(3)}\). So much about the “wisdom” of guidelines! Get a statistical textbook relevant for BE (e.g., Hauschke et al.1 or Chow & Liu2).
— Dif-tor heh smusma 🖖🏼 Довге життя Україна! Helmut Schütz The quality of responses received is directly proportional to the quality of the question asked. 🚮 Science Quotes |
joy_fm ☆ Indonesia, 2014-11-10 02:49 (3448 d 01:07 ago) @ Helmut Posting: # 13847 Views: 5,828 |
|
Hi Helmut, Thank you for your clear and helpful explanation And thank you for sharing your expertise with me. Best Regards joy_fm Thank you for this statement too: Thankfully the BEBA Forum is not a boys-only club. [Helmut] |