smaller errors after including correlations in the fit?
- From: "bigeyes" <voikitza@xxxxxxxxx>
- Date: 2 Dec 2005 19:48:15 -0800
Hi,
I wonder if my code is bugged, please help.
If my fit (based on the Marquardt algorithm)
result for the uncorrelated case
CHI2=SUM_i[(data-theory)/stat error]^2
gives let's say A+/-50
(where I have used only statistical errors)
But for the correlated case, were general chisquared:
CHI2=SUM_ij(data-theory)_i(Vij)^-1(data-theory)_j
where V is the covariance matrix and I add the statistical errors
in quadrature to the diagonal elements
the fit gives A'+/-30
is it physically possible to get smaller errorrs and what does that
mean???
HELP PLEASE!!
.
- Prev by Date: Testing correlation with permutation samples
- Next by Date: Probability of rth order statistic
- Previous by thread: Testing correlation with permutation samples
- Next by thread: Probability of rth order statistic
- Index(es):
Relevant Pages
|
