bilby.core.likelihood.Multinomial

class bilby.core.likelihood.Multinomial(data, n_dimensions, base='parameter_')[source]

Bases: Likelihood

Likelihood for system with N discrete possibilities.

__init__(data, n_dimensions, base='parameter_')[source]
Parameters:
data: array-like

The number of objects in each class

n_dimensions: int

The number of classes

base: str

The base of the parameter labels

__call__(*args, **kwargs)

Call self as a function.

Methods

__init__(data, n_dimensions[, base])

log_likelihood()

Since n - 1 parameters are sampled, the last parameter is 1 - the rest

log_likelihood_ratio()

Difference between log likelihood and noise log likelihood

noise_log_likelihood()

Our null hypothesis is that all bins have probability 1 / nbins, i.e., no bin is preferred over any other.

Attributes

marginalized_parameters

meta_data

log_likelihood()[source]

Since n - 1 parameters are sampled, the last parameter is 1 - the rest

log_likelihood_ratio()[source]

Difference between log likelihood and noise log likelihood

Returns:
float
noise_log_likelihood()[source]

Our null hypothesis is that all bins have probability 1 / nbins, i.e., no bin is preferred over any other.