lmoments3 API

Sample L-moments

lmoments3.lmom_ratios(data, nmom=5)

Estimate nmom number of L-moments from a sample data.

Parameters:

• data (list or array-like sequence) – Sequence of (sample) data

• nmom (int) – number of L-moments to estimate

Returns:

L-moment ratios like this: l1, l2, t3, t4, t5, .. . As in: items 3 and higher are L-moment ratios. # noqa: E501

Return type:

list

Distributions

L-moments for scipy.stats distributions.

class lmoments3.distr.LmomDistrMixin

Mixin class to add L-moment methods to scipy.stats.rv_continous distribution functions.

Distributions using the mixin should override the methods _lmom_fit() and lmom_ratios().

lmom_fit(data=None, lmom_ratios=None)

Fit the distribution function to the given data or given L-moments.

Parameters:

• data (array_like) – Data to use in calculating the distribution parameters

• lmom_ratios (array_like) – L-moments (ratios) l1, l2, t3, t4, .. to use in calculating the distribution parameters

Returns:

Distribution parameters in scipy order, e.g. scale, loc, shape

Return type:

OrderedDict

lmom(*args, nmom=5, **kwds)

Compute the distribution’s L-moments, e.g. l1, l2, l3, l4, ..

Parameters:

• args (float) – Distribution parameters in order of shape(s), loc, scale

• nmom (int) – Number of moments to calculate

• kwds (float) – Distribution parameters as named arguments. See rv_continous.shapes for names of shape parameters

Returns:

List of L-moments

Return type:

list

lmom_ratios(*args, nmom=5, **kwds)

Compute the distribution’s L-moment ratios, e.g. l1, l2, t3, t4, ..

Parameters:

• args (float) – Distribution parameters in order of shape(s), loc, scale

• nmom (int) – Number of moments to calculate

• kwds (float) – Distribution parameters as named arguments. See rv_continous.shapes for names of shape parameters

Returns:

List of L-moment ratios

Return type:

list

nnlf(data, *args, **kwds)

Other statistical functions

Statistics functions for L-moments analysis.

lmoments3.stats.AIC(data, distr_name, distr_paras)

Calculate the Akaike Information Criterion (AIC).

lmoments3.stats.AICc(data, distr_name, distr_paras)

Calculate the corrected Akaike Information Criterion (AICc).

lmoments3.stats.BIC(data, distr_name, distr_paras)

Calculate the Bayesian Information Criterion (BIC).