A quotation from Davenport and Root's book, "Random signals and noise"
(McGraw-Hill 1958) seems appropriate here:
One way to approach the notion of probability is through the phenomenon
of _statistical regularity_. There are many repeating situations in
nature for which we can predict in advance from previous experience
roughly what will happen, or what will happen on the average, but not
exactly what will happen. We say in such cases that the
occurrences are
_random_; in fact the reason for our inability to predict exactly
may be
that (1) we do not know all the causal forces at work, (2) we do not
have enough data about the conditions of the problem, (3) the
forces are
so complicated that calculation of their combined effect is unfeasible,
or possibly (4) there is some basic indeterminacy in the physical world.
(p 5)
The point being that three of the four reasons for describing behavior as
random imply a lack of knowledge or capability on our part, while the
fourth implies a lack of even the possibility of knowledge or capability.
When we say some behavior is random, we are not so much claiming it's not
under any control as admitting that we do not know, and perhaps cannot know
how it is controlled.
Bill Hamilton | Chassis & Vehicle Systems
GM R&D Center | Warren, MI 48090-9055
810 986 1474 (voice) | 810 986 3003 (FAX)
hamilton@gmr.com (office) | whamilto@mich.com (home)