t-test & Welch-test [Power / Sample Size]

posted by Helmut Homepage – Vienna, Austria, 2019-09-14 00:16 (583 d 10:10 ago) – Posting: # 20596
Views: 3,899

Hi Rocco,

» Where does the formula on slide 10.83 in bebac.at/lectures/Leuven2013WS2.pdf for CI for parallel design come from? I cannot seem to find reference anywhere.

Honestly, I don’t remember why I simplified the commonly used formula.
Algebra:$$s\sqrt{\tfrac{n_1+n_2}{n_1n_2}}=\sqrt{s^2(1/n_1+1/n_2)}\;\tiny{\square}$$ Comparison with the data of the example.The formula for Satterthwaite’s approximation of the degrees of freedom given in slide 11 contained typos (corrected in the meantime). Of course,$$\nu\approx\frac{\left(\frac{{s_{1}}^{2}}{n_1}+\frac{{s_{2}}^{2}}{n_2}\right)^2}{\frac{{s_{1}}^{4}}{n{_{1}}^{2}(n_1-1)}+\frac{{s_{2}}^{4}}{n{_{2}}^{2}(n_2-1)}}$$Satterthwaite’s approximation adjusts both for unequal variances and group sizes. The conventional t-test is fairly robust against the former but less so for the latter.
In the [image]-function t.test() var.equal = FALSE is the default because:

Dif-tor heh smusma 🖖
Helmut Schütz

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

Complete thread:

 Admin contact
21,419 posts in 4,475 threads, 1,510 registered users;
online 11 (1 registered, 10 guests [including 4 identified bots]).
Forum time: Monday 10:27 CEST (Europe/Vienna)

There is one certainty in drug development
and statistics that one can depend on:
the data are always late.    Scott Patterson and Byron Jones

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