NOTICE! This is a static HTML version of a legacy LOCI Software ticket.

LOCI projects are now located on GitHub. The Bio-Formats project can be found here.

Ticket #745 (closed enhancement: fixed)

Opened 2012-10-05T12:18:31-05:00

Last modified 2012-11-09T12:34:21-06:00

Show AIC as well as chi-square

Reported by: aivar Owned by: aivar
Priority: major Milestone: slimplugin2.0
Component: slim-plugin Severity: serious
Keywords: Cc: payoung2@…
Blocked By: Blocking:

Description

When choosing between single, double, and triple exponential models the Akaike index is a better criteria to determine which model fits best than just the chi square.

Calculate & show the AIC as well as the current chi square in the fit results.

Change History

comment:1 Changed 2012-11-09T12:34:21-06:00 by aivar

  • Status changed from new to closed
  • Resolution set to fixed

Fixed, may need tweaking.

I am using the formula:

AIC = chi-square + 2k

from  http://en.wikipedia.org/wiki/Akaike_information_criterion

here k is the number of free parameters.

Usually the reduced chi-square gets reported, this is:

chi-square / n - k

here n is the number of data points and k the number of free parameters.