Sum of residuals ~ ε [Design Issues]

posted by PharmCat  – Russia, 2019-12-24 18:40 (274 d 23:57 ago) – Posting: # 21028
Views: 2,845

» I disagree. In the model ε = 0. However in the fit, the sum of residuals is only asymptotically 0. We shouldn’t speak of bias when we obtain something sufficiently close to the numeric resolution of the machine.

Hi Helmut!

I don't mean that we have bias because 0 not equal eps(). Numericaly we can make calculation with values lower that eps() like: (1E-40 + 2E-40) * 3E+40 = 9.0. Problems can start with things like this: 1 + 1E-40, for example: (1E+40 - 1E+40 + 1 == 1E+40 + 1  - 1E+40) == false. - this not what about a try to say.

I try to say, that zero residual (or effective zero residual) can't be at all, "by definition" in linear model.

Complete thread:

Activity
 Admin contact
21,074 posts in 4,394 threads, 1,468 registered users;
online 10 (0 registered, 10 guests [including 2 identified bots]).
Forum time: Thursday 19:37 CEST (Europe/Vienna)

Enlightenment is man’s emergence from his self-imposed nonage
for which he himself was responsible.
Nonage is the inability to use one’s own intellect
without the direction of another.    Immanuel Kant

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