data_parallel: Sample Size Tables for the Parallel Group Design

Description Details Note Author(s) Examples


These data.frames give sample size tables calculated with sampleN.TOST() for the parallel group design (2 groups).


The data.frames can be accessed by their names.

ctSJ.VIII.10 is Table VIII, column ‘level of bioequivalence 10%’ from
Julious SA. Tutorial in Biostatistics. Sample sizes for clinical trials with Normal data.
Stat Med. 2004;23(12):1921–86. doi: 10.1002/sim.1783

Multiplicative model, theta1=0.9, theta2=1.1111 (1/theta1), target power=90%,
power approximate via non-central t-distribution.
Attention! Julious gives sample size per group.

ctSJ.VIII.20 is Table VIII from the same source
column ‘level of bioequivalence 20%’
Multiplicative model, theta1=0.8, theta2=1.25 (1/theta1), target power=90%,
power approximate via non-central t.

ctCW.III is Table III from
Chow SC, Wang H. On Sample Size Calculation in Bioequivalence Trials
J Pharmacokinet Pharmacodyn. 2001. 28(2):155–69.
Additive model, theta1=–0.2, theta2=+0.2 (BE limits 0.80 – 1.20), exact.

Seems the last reference is not very reliable (compare to the Table in the paper).


Scripts for creation of these data.frames can be found in the \test sub-directory of the package.
Comparing the results of these scripts to the corresponding data.frames can be used for validation purposes.





PowerTOST documentation built on Aug. 17, 2017, 5:05 p.m.