sury
★    

India,
2019-04-16 10:44
(1808 d 09:38 ago)

Posting: # 20171
Views: 4,037
 

 Non-inferiority Sample Size Estimation [Power / Sample Size]

Hii All...

Anyone know about the sample size estimation for the non inferiority clinical trials, as per the literatures and some google says to consider the NI Margin to some percentage and estimate the sample size

I have tried to do the same in FARTSSIE23 (Non-inferiority, Parallel), but in addition to that Standard deviation is necessary for the same and in SAS (PROC POWER), we need to provide the CV to estimate the sample size

Can we assume the standard deviation or we need to provide the exact Standard deviation (obtained from the literatures on the drug) ?

Dose the same criteria applicable as that of the ISCV concept for the bio equivalence studies?


Best Regards...


Edit: Category changed; see also this post #1[Helmut]
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2019-04-16 18:53
(1808 d 01:29 ago)

@ sury
Posting: # 20175
Views: 3,501
 

 Non-inferiority Sample Size Estimation

Hi Sury,

❝ […] sample size estimation for the non inferiority clinical trials […] I have tried to do the same in FARTSSIE23 (Non-inferiority, Parallel), but in addition to that Standard deviation is necessary for the same and in SAS (PROC POWER), we need to provide the CV to estimate the sample size


No idea about Proc Power. Let’s try the example of FARTSSIE2.4 (which is based on Julious’ Example 4.1.1.1.*) in PowerTOST:

library(PowerTOST)
design   <- "parallel"            # Well...
desired  <- 0.90                  # Target power
alpha    <- 0.025                 # Probability of type I error
sigma    <- 40                    # Common (pooled) standard deviation
margin   <- 10                    # Maximum allowed difference
mean.A   <- 160                   # Test
mean.B   <- 158                   # Reference
theta0   <- mean.A - mean.B       # Expected difference
if (theta0 > 0) theta0 <- -theta0 # Force non-inferiority
logscale <- FALSE
sampleN.noninf(alpha=alpha, CV=sigma, logscale=logscale, margin=margin,
               theta0=theta0, targetpower=desired, design=design)

Gives

++++++++++++ Non-inferiority test +++++++++++++
            Sample size estimation
-----------------------------------------------
Study design:  2 parallel groups
untransformed data (additive model)

alpha = 0.025, target power = 0.9
Non-inf. margin = 10
True diff. = -2,  CV = 40

Sample size (total)
 n     power
470   0.900652

… which agrees with FARTSSIE2.4

❝ Can we assume the standard deviation …


Sure.

❝ … or we need to provide the exact Standard deviation (obtained from the literatures on the drug) ?


That’s also an estimate. The true value is unknown.

❝ Dose the same criteria applicable as that of the ISCV concept for the bio equivalence studies?


Not sure what you mean here. Can you try to explain?


  • Julious SA. Sample sizes for clinical trials with Normal data. Stat Med. 2004;23(12):1949–50. doi:10.1002/sim.1783

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
sury
★    

India,
2019-04-17 08:55
(1807 d 11:28 ago)

@ Helmut
Posting: # 20180
Views: 3,390
 

 Non-inferiority Sample Size Estimation

Hello

❝ ❝ Can we assume the standard deviation …


❝ Sure.


❝ ❝ … or we need to provide the exact Standard deviation (obtained from the literatures on the drug) ?


❝ That’s also an estimate. The true value is unknown.


❝ ❝ Dose the same criteria applicable as that of the ISCV concept for the bio equivalence studies?


❝ Not sure what you mean here. Can you try to explain?


I mean to say is in normal bio equivalence studies, we need the ISCV information in order to estimate the sample size. Does this same criteria is applicable for the standard deviation for Non-inferiority Trails too?. but i got my answer in the above explanation..:-)

And in addition to that i have one more doubt...

By the above explanation, we dont need any sort of information regarding the drug nature or literature support or pilot studies for the estimation of the sample size?

In general BE studies, we require the pilot study or literature support for the sample size estimation (ISCV) for the pivotal studies.

As we are assuming the margin of error, Standard deviation and the power (Which are required) for the non inferiority trials

Correct me if i am wrong anywhere

BTW, Thanks for your reply. it made me clear about the concept on Non-inferiority trials.:-)


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[Helmut]
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2019-04-17 12:59
(1807 d 07:24 ago)

@ sury
Posting: # 20181
Views: 3,415
 

 Read, read, read!

Hi Sury,

first of all, please delete everything from the text of the original poster which is not necessary in understanding your answer; see also this post #5! We edited 80% of your replies. Hence, this is the first warning.

❝ ❝ ❝ Can we assume the standard deviation …

❝ ❝ Sure.

❝ ❝ ❝ … or we need to provide the exact Standard deviation (obtained from the literatures on the drug) ?

❝ ❝ That’s also an estimate. The true value is unknown.

❝ ❝ ❝ Dose the same criteria applicable as that of the ISCV concept for the bio equivalence studies?

❝ ❝ Not sure what you mean here. Can you try to explain?


❝ I mean to say is in normal bio equivalence studies, we need the ISCV information in order to estimate the sample size. Does this same criteria is applicable for the standard deviation for Non-inferiority Trails too?. but i got my answer in the above explanation..:-)


No, you got it wrong. You can assume something but with a reason!

❝ By the above explanation, we dont need any sort of information regarding the drug nature or literature support or pilot studies for the estimation of the sample size?


Are you kidding? You will administer a drug to healthy volunteers or patients which always carries some risk. Don’t play games.

❝ In general BE studies, we require the pilot study or literature support for the sample size estimation (ISCV) for the pivotal studies.


❝ As we are assuming the margin of error, Standard deviation and the power (Which are required) for the non inferiority trials


❝ Correct me if i am wrong anywhere


Almost everywhere.

❝ it made me clear about the concept on Non-inferiority trials.:-)


Sorry, you got me wrong. The Forum’s Policy states “We expect a basic knowledge of BE/BA or related fields …” – which you are lacking. You shouldn’t rely on anything you find on the internet (including this forum) without a basic understanding.

I strongly recommend to read textbooks on the topic. See this post (always get the latest editions). #1, #3, #11 are good entry points. For sample size estimation additionally:
  • Julious SA. Sample Sizes for Clinical Trials. Boca Raton; Chapman & Hall/CRC; 2010.
Non-Inferiority is covered in Chapter 6 (pp 95–106) and – briefly – in the reference I gave in my pre­vi­ous post (pp 1946–53).

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,636 registered users;
85 visitors (0 registered, 85 guests [including 8 identified bots]).
Forum time: 19:23 CET (Europe/Vienna)

Nothing shows a lack of mathematical education more
than an overly precise calculation.    Carl Friedrich Gauß

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5