WStatCountsStatistic#

class gammapy.stats.WStatCountsStatistic(n_on, n_off, alpha, mu_sig=None)[source]#

Bases: gammapy.stats.counts_statistic.CountsStatistic

Class to compute statistics (significance, asymmetric errors , ul) for Poisson distributed variable with unknown background.

Parameters
n_onint

Measured counts in on region

n_offint

Measured counts in off region

alphafloat

Acceptance ratio of on and off measurements

mu_sigfloat

Expected signal counts in on region

Attributes Summary

error

Approximate error from the covariance matrix.

n_bkg

Known background computed alpha * n_off

n_sig

Excess

p_value

Return p_value of measured excess.

sqrt_ts

Return statistical significance of measured excess.

stat_max

Stat value for best fit hypothesis, i.e. expected signal mu = n_on - alpha * n_off - mu_sig.

stat_null

Stat value for null hypothesis, i.e. mu_sig expected signal counts.

ts

Return stat difference (TS) of measured excess versus no excess.

Methods Summary

compute_errn([n_sigma])

Compute downward excess uncertainties.

compute_errp([n_sigma])

Compute upward excess uncertainties.

compute_upper_limit([n_sigma])

Compute upper limit on the signal.

n_sig_matching_significance(significance)

Compute excess matching a given significance.

sum([axis])

Return summed CountsStatistics.

Attributes Documentation

error#

Approximate error from the covariance matrix.

n_bkg#

Known background computed alpha * n_off

n_sig#

Excess

p_value#

Return p_value of measured excess. Here the value accounts only for the positive excess significance (i.e. one-sided).

sqrt_ts#

Return statistical significance of measured excess. The sign of the excess is applied to distinguish positive and negative fluctuations.

stat_max#

Stat value for best fit hypothesis, i.e. expected signal mu = n_on - alpha * n_off - mu_sig

stat_null#

Stat value for null hypothesis, i.e. mu_sig expected signal counts

ts#

Return stat difference (TS) of measured excess versus no excess.

Methods Documentation

compute_errn(n_sigma=1.0)#

Compute downward excess uncertainties.

Searches the signal value for which the test statistics is n_sigma**2 away from the maximum.

Parameters
n_sigmafloat

Confidence level of the uncertainty expressed in number of sigma. Default is 1.

compute_errp(n_sigma=1)#

Compute upward excess uncertainties.

Searches the signal value for which the test statistics is n_sigma**2 away from the maximum.

Parameters
n_sigmafloat

Confidence level of the uncertainty expressed in number of sigma. Default is 1.

compute_upper_limit(n_sigma=3)#

Compute upper limit on the signal.

Searches the signal value for which the test statistics is n_sigma**2 away from the maximum or from 0 if the measured excess is negative.

Parameters
n_sigmafloat

Confidence level of the upper limit expressed in number of sigma. Default is 3.

n_sig_matching_significance(significance)#

Compute excess matching a given significance.

This function is the inverse of significance.

Parameters
significancefloat

Significance

Returns
n_signumpy.ndarray

Excess

sum(axis=None)[source]#

Return summed CountsStatistics.

Parameters
axisNone or int or tuple of ints, optional

Axis or axes on which to perform the summation. Default, axis=None, will perform the sum over the whole array.

Returns
statCountsStatistics

the return stat object