BE-proff
●    

2016-11-07 22:53
(2697 d 13:11 ago)

Posting: # 16786
Views: 4,787
 

 Formula to calculate sample size [Power / Sample Size]

Hi All,

What is/are formula/as used by sampleN.TOST to calculate sample size of different study designs? :confused:
I am interested in "exact" method.:-)
Helmut
★★★
avatar
Homepage
Vienna, Austria,
2016-11-07 23:10
(2697 d 12:54 ago)

@ BE-proff
Posting: # 16787
Views: 3,664
 

 Formula to calculate sample size

Hi BE-proff,

❝ What is/are formula/as used by sampleN.TOST to calculate sample size of different study designs? :confused:

❝ I am interested in "exact" method.:-)


See this post and the references. Since numeric integration is involved, it is not that easy.

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
d_labes
★★★

Berlin, Germany,
2016-11-08 09:29
(2697 d 02:35 ago)

@ BE-proff
Posting: # 16788
Views: 3,641
 

 Formula to calculate sample size

Dear BE-proff,

❝ What is/are formula/as used by sampleN.TOST to calculate sample size of different study designs? :confused:

❝ I am interested in "exact" method.:-)


additional to Helmut's suggestion I would point you to the \doc sub-directory of the package PowerTOST. It contains a PDF file BE_power_sample_size_excerpt.pdf which deals in a short cursory manner with power / sample size estimation of the TOST procedure.

As you will see there is no distinct (simple) formula for sample size estimation. Only the power (given CV and n and additionally some design characteristic) can be calculated. The sample size is then iteratively obtained by varying n until the desired power is achieved.

Hope this helps.

Regards,

Detlew
UA Flag
Activity
 Admin contact
22,957 posts in 4,819 threads, 1,639 registered users;
81 visitors (1 registered, 80 guests [including 3 identified bots]).
Forum time: 12:04 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