[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Can't generate perfect theoretic standard normal.
I can't take the minute differences in this thread very seriously
but I think I recall, for what it's worth, that the late Gunnar Blom
recommended (in this notation) (_n - 3/8) / (_N + 3/4)
as a plotting position for (near) Gaussian data.
* For searches and help try: