On Sat, 03 Jan 2004 16:23:33 GMT, "R. Martin" <[EMAIL PROTECTED]> wrote:
> Herman Rubin wrote: > > [ snip, original question] > > > > BTW, the earliest treatment I know for outliers was for > > astronomy and physics in the 19th century. There, the > > effect of improperly discarding suspected outliers was > > primarily an affordable loss of efficiency, but biases also > > resulted. The published values of the speed of light kept > > decreasing until really good observations were made, as the > > first values were high, and outliers were rejected, partly > > using previous experiments. > > IIRC there have been other cases of values of fundmental constants > and elementary particle parameters being determined to be well > outside of the "limits" set by earlier work. Yes, but - to some extent - that is a bogus, misleading observation. That is, the measurements were *effectively* that precise; you could successfully use them as if they were that precise, in all those formulas that make use of the other constants. However, that whole set of "fundamental constants" is reviewed, now and again. There are relatively few experiments that offer evidence about one constant without relying on assumptions about the other constants -- or so I recall, from an excellent Scientific American article, probably in 1986, about the CODATA revisions of that time. Here is a recent page - http://physics.nist.gov/cuu/Constants/index.html?/codata86.html -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html "Taxes are the price we pay for civilization." . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
