[Numpy-tickets] [NumPy] #502: Unbiased estimates of variance/ std deviation
NumPy
numpy-tickets@scipy....
Sun May 13 11:24:24 CDT 2007
#502: Unbiased estimates of variance/ std deviation
-------------------------+--------------------------------------------------
Reporter: pierregm | Owner: somebody
Type: enhancement | Status: new
Priority: low | Milestone: 1.1
Component: Other | Version: none
Severity: trivial | Resolution:
Keywords: |
-------------------------+--------------------------------------------------
Comment (by rkern):
My preference is to not use the term "bias," since it's wrong. The
standard definition of bias, E[X-Xtrue], is inappropriate for quantities
like variance and standard deviation. Notably, the square root of the N-1,
"unbiased" variance is *not* an unbiased estimate of the standard
deviation. Using an appropriate definition of bias, E[log(X/Xtrue)], does
give coherent estimates of variance and standard deviation. However, the
factor is N-2, not N-1.
My preference is to add a parameter that is subtracted from N rather than
a flag that switches between N and N-1. The shortest name a I can come up
with is a bit obscure, though, "ddof" for "change in degrees of freedom".
--
Ticket URL: <http://projects.scipy.org/scipy/numpy/ticket/502#comment:3>
NumPy <http://projects.scipy.org/scipy/numpy>
The fundamental package needed for scientific computing with Python.
More information about the Numpy-tickets
mailing list