Class Model_selection

Instance Methods

__init__(self, relax)
Class containing functions specific to model selection.

select(self, method=None, modsel_run=None, runs=None)
Model selection function.

aic(self, chi2, k, n)
Akaike's Information Criteria (AIC).

aicc(self, chi2, k, n)
Small sample size corrected AIC.

bic(self, chi2, k, n)
Bayesian or Schwarz Information Criteria.

tests(self, run)
Function containing tests the given run.

Method Details

aic(self, chi2, k, n)

Akaike's Information Criteria (AIC).

The formula is:

    AIC = chi2 + 2k

where:
    chi2 is the minimised chi-squared value.
    k is the number of parameters in the model.

aicc(self, chi2, k, n)

Small sample size corrected AIC.

The formula is:

                       2k(k + 1)
    AICc = chi2 + 2k + ---------
                       n - k - 1

where:
    chi2 is the minimised chi-squared value.
    k is the number of parameters in the model.
    n is the dimension of the relaxation data set.

bic(self, chi2, k, n)

Bayesian or Schwarz Information Criteria.

The formula is:

    BIC = chi2 + k ln n

where:
    chi2 - is the minimised chi-squared value.
    k - is the number of parameters in the model.
    n is the dimension of the relaxation data set.