[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Help-gsl] the linear regression: gsl_fit_linear had gave an unexpec
|
From: |
Sergey Shcherbina |
|
Subject: |
Re: [Help-gsl] the linear regression: gsl_fit_linear had gave an unexpected unreality |
|
Date: |
Fri, 21 Jul 2017 14:55:07 +0300 |
The Model data for gsl_fit_linear was calculated excellently!
But reality is other:
# best fit: Y = -5424468603777.739258 + 3616.427002 X
# covariance matrix:
# [ 1.59747e+24, -1.06501e+15
# -1.06501e+15, 710030]
# chisq= 3.96039e+12
This number is not correct - -5424468603777.739258 ...
Real data on a plot and it is in attached file.
Real regression ax+b: 1.77307*x-7913.67
Regards,
Sergey.
TestLinearRegresRealEDatax002a.png
Description: PNG image
TestLinearRegresRealEDatax002a.png