MixtureCureFitter

class lifelines.fitters.mixture_cure_fitter.MixtureCureFitter(base_fitter, *args, **kwargs)

This class implements a Mixture Cure Model for univariate data with a configurable distribution for the non-cure portion. The model survival function has parameterized form:

\[S(t) = c + \left(1 - c\right)S_b(t), \;\; 1 > c > 0\]

where \(S_b(t)\) is a parametric survival function describing the non-cure portion of the population, and \(c\) is the cured fraction of the population.

After calling the .fit method, you have access to properties like: cumulative_hazard_, survival_function_, lambda_ and rho_. A summary of the fit is available with the method print_summary(). The parameters for both the cure portion of the model and from the base_fitter are available. The cure fraction is called cured_fraction_, and parameters from the base_fitter will be available with their own appropriate names.

Parameters:
  • base_fitter (ParametricUnivariateFitter, required) – an instance of a fitter that describes the non-cure portion of the population.

  • alpha (float, optional (default=0.05)) – the level in the confidence intervals.

Important

The base_fitter instance is used to describe the non-cure portion of the population, but is not actually fit to the data. Some internal properties are modified, and it should not be used for any other purpose after passing it to the constructor of this class.

Examples

from lifelines import MixtureCureFitter, ExponentialFitter

fitter = MixtureCureFitter(base_fitter=ExponentialFitter())
fitter.fit(T, event_observed=observed)
print(fitter.cured_fraction_)
print(fitter.lambda_)  # This is available because it is a parameter of the ExponentialFitter
cumulative_hazard_

The estimated cumulative hazard (with custom timeline if provided)

Type:

DataFrame

cured_fraction_

The fitted parameter \(c\) in the model

Type:

float

hazard_

The estimated hazard (with custom timeline if provided)

Type:

DataFrame

survival_function_

The estimated survival function (with custom timeline if provided)

Type:

DataFrame

cumulative_density_

The estimated cumulative density function (with custom timeline if provided)

Type:

DataFrame

variance_matrix_

The variance matrix of the coefficients

Type:

DataFrame

median_survival_time_

The median time to event

Type:

float

durations

The durations provided

Type:

array

event_observed

The event_observed variable provided

Type:

array

timeline

The time line to use for plotting and indexing

Type:

array

entry

The entry array provided, or None

Type:

array or None

percentile(p)

Return the unique time point, t, such that S(t) = p.

Parameters:

p (float)