Fit the ARA model. Parameters ---------- x : array_like An array of event times. i : array_like

Create a model instance directly from parameters without fitting. Parameters ---------- params: array_like

r""" The quantile function for a distribution using the parameters found in the ``.params`` attribute. Parameters --

Main handler that ensures any input to a surpyval fitter meets the requirements to be used in one of the parametric or nonparametric fitters.

r""" Confidence bounds of the ``on`` function at the ``alpa_ci`` level of significance. Can be the upper, lower, or two-sided confiden

r""" The mean of the distribution using the parameters found in the ``.params`` attribute. Returns ------- me

r""" The central feature to SurPyval's capability. This function aimed to have an API to mimic the simplicity of the scipy API. That i

Takes in the fsli format and ensures that the data is correctly defined. Takes an assorted combination of f, s, l, and i and returns them in

r""" The Laplace (centroid) trend test for recurrent-event data. Under the null hypothesis that the events of each system follow a homoge

Converts the data into the xrd format. If the data has right truncated observations or left or interval censored observations, the da

Estimate the mean cumulative function (MCF) at ``x``. These models have no closed-form cumulative intensity, so the MCF is e

Cumulative intensity function (CIF) of the HPP model. Parameters ---------- x : array_like The values at

Build an ARA model from given parameters. Parameters ---------- params : list Parameters for the underl

r""" Fit the Binomial distribution for a known number of trials, ``n_trials``, using the closed-form maximum likelihood estimate of

Takes a combination of 'x', 'r', and 'd' arrays and ensures that the data is feasible. Does not check for the case where r is always dec

Resolve and assign the fitted model's support interval. For an offset model the left edge is the fitted ``gamma``; otherwise each edg

The central feature to SurPyval's capability. This function aimed to have an API to mimic the simplicity of the scipy API. That is,

This function takes in data in the xcnt format and outputs an approximation of the CDF. This function can be used to produce estimates of F u

Create an Accelerated Failure Time fitter for the given distribution. Uses exp(beta'Z) as the acceleration factor — the standard statistical

Create a Proportional Odds fitter for the given distribution. Uses exp(beta'Z) as the odds multiplier — the standard parameterisation fo

Method to add covariates to the data. The covariates are stored in the Z attribute of the object. When doing regression survival anal

r""" Simultaneous confidence band of the survival function. The pointwise bounds from ``cb()`` cover the true value of the su

This function is used to transform the parameters from the bounded parameter space to the unbounded parameter space. This is an improvement

r""" The Military Handbook (MIL-HDBK-189C) trend test for recurrent-event data. Derived from the power-law (Crow-AMSAA) NHPP, the statistic

Serialize SurpyvalData to JSON format. Parameters ---------- filepath : str | Path, optional If provided

r""" Confidence bounds of the survival function computed with a non-parametric bootstrap: the data are resampled with replacem

Return ``(x, c, xl, xr, tl, tr)`` arrays for series ``d``.

Alias of :meth:`cdf` for consistency with surpyval naming.

Kendall's tau. Default: empirical estimate from a large sample.

Method to calculate the confidence bound on a parameter.

Converts the xcn format to the xrd format. Parameters ---------- x: array array of values of variable for which observations

Derive an initial parameter vector for the iterative fitters. Builds a working copy of the data with interval- and left-censored poin

Convert ``Z`` to a numeric design matrix. If a pandas DataFrame is passed and the model was fit from a DataFrame, the covari

Transform one dimension's data into copula (u-space) arrays.

Intensity reduction ``R_n`` in force just after the most recent failure for the Arithmetic Reduction of Intensity model with memory ``m`` (Do

Compute the cumulative incidence function of the model with the parameters found by the fit method. Parameters ----

Simulate count-terminated recurrence data based on the fitted model. Parameters ---------- events: int

Fit the ARA model from recurrent data. Parameters ---------- data : RecurrentData Data containing the r

Call log_rank_split() from x-Z-c arrays.

``d2C/du dv`` -- the copula density. autograd default.

A method to do a probability plot Parameters ---------- heuristic : {'Blom', 'Median', 'ECDF', 'Modal', 'Midpoint',

Function to get the indices for a given vector of x values

Per-row log-likelihood for two prepared dimensions ``d0, d1``.

r""" The density function for a distribution using the parameters found in the ``.params`` attribute. Parameters ---

r""" The entropy of the distribution using the parameters found in the ``.params`` attribute. Returns -------

Parameters ---------- x : array like, optional Array of observations of the random variables. If x is

Finds the previous event time for each event. This is useful for calculating the time since the last event. This method returns the

Draw ``(u, v)`` pairs by conditional inversion of the h-function. ``u`` is uniform; given ``u`` and a uniform ``w``, ``v`` solves ``d

Standard errors of the fitted parameters (the square roots of the diagonal of :meth:`covariance`), ordered to match :attr:`pa

Simulate time-terminated recurrence data based on the fitted model. Parameters ---------- T: float Time

r""" The variance of the distribution using the parameters found in the ``.params`` attribute. Returns -------

Store the fit artefacts and the attributes :class:`LikelihoodInferenceMixin` needs: ``_neg_ll`` (the negative log-likelihood

Clamp the truncation bounds to the distribution's support. Returns the left and right truncation arrays with any value that falls out

Empirical Kendall's tau over rows where both dims are observed.

Drive the multi-start fit. ``fit_once(x0) -> OptimizeResult`` runs the optimiser from a single natural-space start ``x0``. With no us

Simulate count-terminated recurrence data and return the raw events. Unlike :meth:`count_terminated_simulation` (which returns the f

``dC/du`` -- the h-function. autograd default; override if known.

The cumulative density function of the fitted model. Parameters ---------- x : array like The values at