Why does this article mention software? Estimation is a much, much broader topic than that. It's a way of using math to cope with the world, isn't it? In industry, estimation probably is most often associated with estimating the construction cost of buildings. Software development seems a very small part of the story of estimation.
There is also estimation in the Harry Van Trees sense, applied to random variables, where we use statistical knowledge to estimate the value of a variable we can't observe based on some other variable that we can observe. There are various special cases of this such as detection, where the hidden variable is a boolean. Estimation is some of the mathematics behind modems and radars. (The hidden variable for the modem is "what bit did the sender think he was sending?" and for the radar "is there an aircraft up there, and what is its precise ___location?"). The same math is also used in medical imaging.
http://www.amazon.com/exec/obidos/tg/detail/-/0471095176/104-9158830-1284763
I took this course a few years back and it was way cool. I know MIT is working on putting their lecture notes online, I'm really looking forward to when this course is there.
- This antedates Harry Van Trees! See Lehmann's book Theory of Point Estimation. Ronald Fisher is one of the big names in estimation theory. Michael Hardy 16:14, 18 Dec 2003 (UTC)