Balaji Junior India, 20151123 13:39 Posting: # 15653 Views: 6,639 

Can anyone tell me how to calculate Inter subject variability for parallel design using phoenix winnonlin or manually i can find only Var(Residual) in final variance parameters sheet in Winnonlin while calculating average bioequivalence Thanks in Advance 
Helmut Hero Vienna, Austria, 20151123 15:07 @ Balaji Posting: # 15655 Views: 5,815 

Hi Balaji, » Can anyone tell me how to calculate Inter subject variability for parallel design… That’s a common misconception. The fact that you administered products only once does not mean that the intrasubject variability does not exist (you observed only one occasion). You can calculate the intersubject variability only in a crossover design. In a parallel design you get only the total (or pooled) variability, which consists of both inter and intrasubject components. Talking of intersubject variability in parallel designs is sloppy terminology. » … using phoenix winnonlin or manually i can find only Var(Residual) in final variance parameters sheet in Winnonlin while calculating average bioequivalence Correct. I would not suggest to assume equal variances in groups (see the FDA’s 2001 guidance). Example dataset:
PE 48.58% (90% CI: 27.15–86.94%). Levene’s test for equality of variances is significant (p 0.0229). The conventional ttest is liberal in the case of unequal variances and even more sensitive to unequal group sizes. Personally I would not apply pretesting and use the WelchSatterthwaite adjustment in all cases. In PHX/WNL add a column “period” to the data (containing 1 in all rows). Map trt to Formulation , var to Dependent , subj and period to Classification . Keep trt as the fixed effect and add a repeated specification to the variance structure: repeated = period , variance blocking variables = subj , group = trt , type = variance components . This specification gives:PE 48.58% (90% CI: 26.78–88.14%) – which is wider (conservative). In the conventional analysis the total CV is 100√ℯ^{Var(Residual)}–1 = 80.54%. In the modified analysis you can estimate the total CV separately for T and R, where in PHX/WNL Var(period*trt*subj)_11 is the one of R and Var(period*trt*subj)_12 the one of T. From these variances we get a total CV of 46.23% for R and 111.34% for T.Variances (but not CVs) are additive. Since group sizes are equal, we don’t have to worry about weighting by the degrees of freedom. The residual variance in the default model is 0.5000. The one of R is 0.1937 and the one of T 0.8063. Hence, (0.1937+0.8063)/2=0.5000. ∎ — Cheers, Helmut Schütz The quality of responses received is directly proportional to the quality of the question asked. ☼ Science Quotes 
Balaji Junior India, 20151124 07:14 @ Helmut Posting: # 15657 Views: 5,522 

Thanks Helmut so we can use total variability instead of (inter subject variability and intra subject variability) for parallel design using this 100√ℯVar(Residual)–1 but winnonlin wont calculate total cv we have to calculate manually am I right 
Helmut Hero Vienna, Austria, 20151124 12:58 @ Balaji Posting: # 15661 Views: 5,507 

Hi Balaji, » so we can use total variability instead of (inter subject variability and intra subject variability) for parallel design… Not instead of… In a parallel design the total variability is all we have. Again: Inter and intrasubject variabilities are not accessible, only their sum! » …using this 100√ℯVar(Residual)–1 I strongly advise to use the modified setup (see the “Phoenix WinNonlin 6.4 User’s Guide”, p85–6). » …but winnonlin wont calculate total cv we have to calculate manually Manually? Set up a custom transformation in the Data Wizard.
— Cheers, Helmut Schütz The quality of responses received is directly proportional to the quality of the question asked. ☼ Science Quotes 
Balaji Junior India, 20151124 13:44 @ Helmut Posting: # 15663 Views: 5,511 

Again Thanks Helmut So your saying by using data wizard is the only way to calculate total cv we wont get it by changing some settings 
Helmut Hero Vienna, Austria, 20151124 14:09 @ Balaji Posting: # 15664 Views: 5,575 

Hi Balaji, » So your saying by using data wizard is the only way to calculate total cv Correct. » we wont get it by changing some settings Yes. Why are you confused? What about RTFMs? Relevant ones: “Phoenix WinNonlin 6.4 User’s Guide” and “Data Tools and Plots Guide”. 784 pages. There is no free lunch. If you have difficulties with the setup, I suggest to register at Certara’s forum. There you could upload your projectfile. — Cheers, Helmut Schütz The quality of responses received is directly proportional to the quality of the question asked. ☼ Science Quotes 