weiguo2122 ☆ 2025-01-13 21:19 (30 d 14:24 ago) Posting: # 24339 Views: 569 |
|
FDA “Draft Guidance on Budesonide” part 5, provides Recommendation Related to the Population Bioequivalence (PBE) Statistical Analysis Procedure (Step 3): a. If SigmaR is greater than 0.1, the reference-scaled procedure should be used. b. If SigmaR is less or equal to 0.1, then the constant-scaled procedure should be used. However, when stage (m) is 1, SigmaR cannot be defined because the calculation for MSWk cannot proceed when m = 1 (see formula for MSWk in the guidance). ![]() ![]() What approach should be used to calculate PBE when m = 1? Are there any alternative methods or approaches recommended in this scenario? I have attached formula from Draft Guidance on Budesonide for reference. Thanks for replying and suggesting! |
ElMaestro ★★★ Denmark, 2025-01-13 22:08 (30 d 13:36 ago) @ weiguo2122 Posting: # 24340 Views: 503 |
|
Hello Weiguo2122, ❝ What approach should be used to calculate PBE when m = 1? Are there any alternative methods or approaches recommended in this scenario? When m=1 you have a between units variation (MSB = Mean Square Between) but you do not have a within-unit-variation (MSW = Mean Square Within). A mean square is a variance. The square root of a variance is a standard deviation. You see, at m=1 the entire right-hand side of whatever is under the square root sign disappears. So, at m=1 the stdev for ref is the square root of MSB for that formulation. ![]() — Pass or fail! ElMaestro |
weiguo2122 ☆ 2025-01-15 21:45 (28 d 13:58 ago) @ ElMaestro Posting: # 24341 Views: 417 |
|
Hi ElMaestro, Thank you for your reply. Based on your suggestion, I have been working with a set of code ![]() ![]() Edit: Full quote removed. Please delete everything from the text of the original poster which is not necessary in understanding your answer; see also this post #5! [Ohlbe] |