On Thu, 19 Jan 2006, Russell McMahon wrote: >>> The bell curve situation fits all processors, or anything else we could >> >> The bell curve fits random distributions constrained by one constraint >> with equal 'resistance' for all points. When this is not true then it is >> not a bell curve. > > ie 'normal' or 'Gaussian' distribution. Much doesn't work that way, > but much does. (eg a need to calculate death-by-horse-kick > distribution when horses were a major transportation engine led to the > formulation of the (eponymous) Poisson distribution). The bell curve only works for *one* variable and a certain (random) bias of the data points, and for a large number of points, afaik. Too many conditions for anything but an ideal situation. Peter -- http://www.piclist.com PIC/SX FAQ & list archive View/change your membership options at http://mailman.mit.edu/mailman/listinfo/piclist