WinnieH
☆

Sweden,
2023-01-04 14:33
(32 d 13:22 ago)

Posting: # 23417
Views: 532

## Questions on under­standing the 4-way RSABE method SAS code [RSABE / ABEL]

Dear all,

I am a new learner and I am trying on understanding the 4-way RSABE method SAS code provided by FDA:
/*Intermediate analysis – ilat*/  proc mixed data=scavbe;   class seq;   model ilat =seq/ddfm=satterth;   estimate 'average' intercept 1 seq 0.5 0.5/e cl alpha=0.1;   ods output CovParms=iout1;   ods output Estimates=iout2;   ods output NObs=iout3; run; data ilat;   set iout2;   pointest=exp(estimate);   x=estimate**2-stderr**2;   boundx=(max((abs(lower)),(abs(upper))))**2; /*Intermediate analysis – dlat*/  proc mixed data=scavbe;   class seq;   model dlat=seq/ddfm=satterth; estimate 'average' intercept 1 seq 0.5 0.5/e cl alpha=0.1;   ods output CovParms=dout1;   ods output Estimates=dout2;   ods output NObs=dout3; run; data dlat;   merge dout1(keep=estimate) dout2(keep=df);   s2wr=estimate/2;   dfd=df; run; /*Criterion Bound */  data results;   merge ilat(keep=pointest x boundx) dlat(keep=s2wr dfd);   theta=((log(1.25))/0.25)**2;   y=-theta*s2wr;   boundy=y*dfd/cinv(0.95,dfd);   sWR=sqrt(s2wr);   critbound=(x+y)+sqrt(((boundx-x)**2)+((boundy-y)**2)); run;

I found some discussion about the S2wr and it is really helpful to me. About the ilat, my understanding is that the model is a simple linear model and the estimate is the least square mean. My R code example is as follows:
   mod<-lm(ilat~SEQ, dataset)   result <- confint(emmeans(mod, specs=~1), level = 0.9)   pointest <- exp(result$emmean) x <- (result$emmean)^2- (result$SE)^2 boundx <-(max(c(abs(result$lower.CL), abs(result\$upper.CL))))^2 
My question is 1) how to interpret x and critbound=(x+y)+sqrt(((boundx-x)**2)+((boundy-y)**2))? Is there any related explanation about them? 2) Has anyone tried to reproduce this FDA code in R before? I would like to get some hints from you Thank you very much and wish you a happy new year!

Bests,
Winnie
Helmut
★★★  Vienna, Austria,
2023-01-04 15:02
(32 d 12:53 ago)

@ WinnieH
Posting: # 23418
Views: 465

## Questions on understanding the 4-way RSABE method SAS code

Hi Winnie,

❝ I am a new learner and I am trying on understanding the 4-way RSABE method SAS code provided by FDA: […]

❝ I found some discussion about the S2wr and it is really helpful to me. About the ilat, my understanding is that the model is a simple linear model and the estimate is the least square mean.

I don’t speak SAS but isn’t it a restricted maximum likelihood estimate?

❝ My R code example is as follows: […]

I’m short in time right now; compare it to Detlew’s script in base R.

❝ My question is 1) how to interpret x and critbound=(x+y)+sqrt(((boundx-x)**2)+((boundy-y)**2))? Is there any related explanation about them?

Haha, ‘the unknown x’. I’m aware of only one reference,* which is – regrettably – not in the public domain.
• The statistical approach we use is very similar to that proposed by Tothfalusi,
Endrenyi, et al. 2001, with a minor difference (use of an unbiased estimator for
(μTμR)2).

• Schuirmann D. U.S. FDA Perspective: Statistical Aspects of OGD’s Approach to Bioequivalence (BE) As­sess­ment for Highly Variable Drugs. Presentation at the 2nd conference of The Global Harmonisation Ini­ti­a­tive (GBHI). Rockville. September 15–16, 2016.

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
WinnieH
☆

Sweden,
2023-01-04 16:12
(32 d 11:43 ago)

@ Helmut
Posting: # 23419
Views: 450

## Questions on understanding the 4-way RSABE method SAS code

Hi Helmut,

Best regards,
Zhe  Ing. Helmut Schütz 