Reference/API#

astropy.stats Package#

This subpackage contains statistical tools provided for or used by Astropy.

While the scipy.stats package contains a wide range of statistical tools, it is a general-purpose package, and is missing some that are particularly useful to astronomy or are used in an atypical way in astronomy. This package is intended to provide such functionality, but not to replace scipy.stats if its implementation satisfies astronomers’ needs.

Functions#

binned_binom_proportion(x, success[, bins, ...])

Binomial proportion and confidence interval in bins of a continuous variable x.

binom_conf_interval(k, n[, ...])

Binomial proportion confidence interval given k successes, n trials.

bootstrap(data[, bootnum, samples, bootfunc])

Performs bootstrap resampling on numpy arrays.

cdf_from_intervals(breaks, totals)

Construct a callable piecewise-linear CDF from a pair of arrays.

fold_intervals(intervals)

Fold the weighted intervals to the interval (0,1).

histogram_intervals(n, breaks, totals)

Histogram of a piecewise-constant weight function.

interval_overlap_length(i1, i2)

Compute the length of overlap of two intervals.

kuiper(data[, cdf, args])

Compute the Kuiper statistic.

kuiper_false_positive_probability(D, N)

Compute the false positive probability for the Kuiper statistic.

kuiper_two(data1, data2)

Compute the Kuiper statistic to compare two samples.

mad_std(data[, axis, func, ignore_nan])

Calculate a robust standard deviation using the median absolute deviation (MAD).

median_absolute_deviation(data[, axis, ...])

Calculate the median absolute deviation (MAD).

poisson_conf_interval(n[, interval, sigma, ...])

Poisson parameter confidence interval given observed counts.

signal_to_noise_oir_ccd(t, source_eps, ...)

Computes the signal to noise ratio for source being observed in the optical/IR using a CCD.

biweight_location(data[, c, M, axis, ignore_nan])

Compute the biweight location.

biweight_midcorrelation(x, y[, c, M, ...])

Compute the biweight midcorrelation between two variables.

biweight_midcovariance(data[, c, M, ...])

Compute the biweight midcovariance between pairs of multiple variables.

biweight_midvariance(data[, c, M, axis, ...])

Compute the biweight midvariance.

biweight_scale(data[, c, M, axis, ...])

Compute the biweight scale.

sigma_clip(data[, sigma, sigma_lower, ...])

Perform sigma-clipping on the provided data.

sigma_clipped_stats(data[, mask, ...])

Calculate sigma-clipped statistics on the provided data.

jackknife_resampling(data)

Performs jackknife resampling on numpy arrays.

jackknife_stats(data, statistic[, ...])

Performs jackknife estimation on the basis of jackknife resamples.

circcorrcoef(alpha, beta[, axis, ...])

Computes the circular correlation coefficient between two array of circular data.

circmean(data[, axis, weights])

Computes the circular mean angle of an array of circular data.

circmoment(data[, p, centered, axis, weights])

Computes the p-th trigonometric circular moment for an array of circular data.

circstd(data[, axis, weights, method])

Computes the circular standard deviation of an array of circular data.

circvar(data[, axis, weights])

Computes the circular variance of an array of circular data.

rayleightest(data[, axis, weights])

Performs the Rayleigh test of uniformity.

vonmisesmle(data[, axis, weights])

Computes the Maximum Likelihood Estimator (MLE) for the parameters of the von Mises distribution.

vtest(data[, mu, axis, weights])

Performs the Rayleigh test of uniformity where the alternative hypothesis H1 is assumed to have a known mean angle mu.

bayesian_blocks(t[, x, sigma, fitness])

Compute optimal segmentation of data with Scargle's Bayesian Blocks.

calculate_bin_edges(a[, bins, range, weights])

Calculate histogram bin edges like numpy.histogram_bin_edges.

freedman_bin_width(data[, return_bins])

Return the optimal histogram bin width using the Freedman-Diaconis rule.

histogram(a[, bins, range, weights])

Enhanced histogram function, providing adaptive binnings.

knuth_bin_width(data[, return_bins, quiet])

Return the optimal histogram bin width using Knuth's rule.

scott_bin_width(data[, return_bins])

Return the optimal histogram bin width using Scott's rule.

akaike_info_criterion(log_likelihood, ...)

Computes the Akaike Information Criterion (AIC).

akaike_info_criterion_lsq(ssr, n_params, ...)

Computes the Akaike Information Criterion assuming that the observations are Gaussian distributed.

bayesian_info_criterion(log_likelihood, ...)

Computes the Bayesian Information Criterion (BIC) given the log of the likelihood function evaluated at the estimated (or analytically derived) parameters, the number of parameters, and the number of samples.

bayesian_info_criterion_lsq(ssr, n_params, ...)

Computes the Bayesian Information Criterion (BIC) assuming that the observations come from a Gaussian distribution.

Classes#

SigmaClip([sigma, sigma_lower, sigma_upper, ...])

Class to perform sigma clipping.

SigmaClippedStats(data, *[, mask, ...])

Class to calculate sigma-clipped statistics on the provided data.

Events([p0, gamma, ncp_prior])

Bayesian blocks fitness for binned or unbinned events.

FitnessFunc([p0, gamma, ncp_prior])

Base class for bayesian blocks fitness functions.

PointMeasures([p0, gamma, ncp_prior])

Bayesian blocks fitness for point measures.

RegularEvents(dt[, p0, gamma, ncp_prior])

Bayesian blocks fitness for regular events.

RipleysKEstimator(area[, x_max, y_max, ...])

Estimators for Ripley's K function for two-dimensional spatial data.

Class Inheritance Diagram#

Inheritance diagram of astropy.stats.sigma_clipping.SigmaClip, astropy.stats.sigma_clipping.SigmaClippedStats, astropy.stats.bayesian_blocks.Events, astropy.stats.bayesian_blocks.FitnessFunc, astropy.stats.bayesian_blocks.PointMeasures, astropy.stats.bayesian_blocks.RegularEvents, astropy.stats.spatial.RipleysKEstimator