RegressionKink#

class causalpy.pymc_experiments.RegressionKink[source]#

A class to analyse sharp regression kink experiments.

Parameters:

data (DataFrame) – A pandas dataframe
formula (str) – A statistical model formula
kink_point (float) – A scalar threshold value at which there is a change in the first derivative of the assignment function
model – A PyMC model
running_variable_name (str) – The name of the predictor variable that the kink_point is based upon
epsilon (float) – A small scalar value which determines how far above and below the kink point to evaluate the causal impact.
bandwidth (float) – Data outside of the bandwidth (relative to the discontinuity) is not used to fit the model.

Methods

`RegressionKink.__init__`(data, formula, ...)
`RegressionKink.plot`([round_to])	Plot the results
`RegressionKink.print_coefficients`([round_to])	Prints the model coefficients
`RegressionKink.summary`([round_to])	Print text output summarising the results

Attributes

`expt_type`
`idata`	Access to the models InferenceData object
`model`

__init__(data, formula, kink_point, model=None, running_variable_name='x', epsilon=0.001, bandwidth=inf, **kwargs)[source]#

Parameters: