InstrumentalVariableRegression#

class causalpy.pymc_models.InstrumentalVariableRegression[source]#

Custom PyMC model for instrumental linear regression

Example

>>> import causalpy as cp
>>> import numpy as np
>>> from causalpy.pymc_models import InstrumentalVariableRegression
>>> N = 10
>>> e1 = np.random.normal(0, 3, N)
>>> e2 = np.random.normal(0, 1, N)
>>> Z = np.random.uniform(0, 1, N)
>>> ## Ensure the endogeneity of the the treatment variable
>>> X = -1 + 4 * Z + e2 + 2 * e1
>>> y = 2 + 3 * X + 3 * e1
>>> t = X.reshape(10,1)
>>> y = y.reshape(10,1)
>>> Z = np.asarray([[1, Z[i]] for i in range(0,10)])
>>> X = np.asarray([[1, X[i]] for i in range(0,10)])
>>> COORDS = {'instruments': ['Intercept', 'Z'], 'covariates': ['Intercept', 'X']}
>>> sample_kwargs = {
...     "tune": 5,
...     "draws": 10,
...     "chains": 2,
...     "cores": 2,
...     "target_accept": 0.95,
...     "progressbar": False,
... }
>>> iv_reg = InstrumentalVariableRegression(sample_kwargs=sample_kwargs)
>>> iv_reg.fit(X, Z,y, t, COORDS, {
...                  "mus": [[-2,4], [0.5, 3]],
...                  "sigmas": [1, 1],
...                  "eta": 2,
...                  "lkj_sd": 1,
...              }, None)
Inference data...

Methods

`InstrumentalVariableRegression.__init__`([...])
`InstrumentalVariableRegression.add_coord`(name)	Registers a dimension coordinate with the model.
`InstrumentalVariableRegression.add_coords`(...)	Vectorized version of `Model.add_coord`.
`InstrumentalVariableRegression.add_named_variable`(var)	Add a random graph variable to the named variables of the model.
`InstrumentalVariableRegression.build_model`(X, ...)	Specify model with treatment regression and focal regression data and priors
`InstrumentalVariableRegression.calculate_cumulative_impact`(impact)
`InstrumentalVariableRegression.calculate_impact`(...)
`InstrumentalVariableRegression.check_start_vals`(start)	Check that the starting values for MCMC do not cause the relevant log probability to evaluate to something invalid (e.g. Inf or NaN).
`InstrumentalVariableRegression.compile_d2logp`([...])	Compiled log probability density hessian function.
`InstrumentalVariableRegression.compile_dlogp`([...])	Compiled log probability density gradient function.
`InstrumentalVariableRegression.compile_fn`(outs, *)	Compiles an PyTensor function
`InstrumentalVariableRegression.compile_logp`([...])	Compiled log probability density function.
`InstrumentalVariableRegression.create_value_var`(...)	Create a `TensorVariable` that will be used as the random variable's "value" in log-likelihood graphs.
`InstrumentalVariableRegression.d2logp`([...])	Hessian of the models log-probability w.r.t.
`InstrumentalVariableRegression.debug`([...])	Debug model function at point.
`InstrumentalVariableRegression.dlogp`([vars, ...])	Gradient of the models log-probability w.r.t.
`InstrumentalVariableRegression.eval_rv_shapes`()	Evaluates shapes of untransformed AND transformed free variables.
`InstrumentalVariableRegression.fit`(X, Z, y, ...)	Draw samples from posterior distribution and potentially from the prior and posterior predictive distributions.
`InstrumentalVariableRegression.initial_point`([...])	Computes the initial point of the model.
`InstrumentalVariableRegression.logp`([vars, ...])	Elemwise log-probability of the model.
`InstrumentalVariableRegression.logp_dlogp_function`([...])	Compile an PyTensor function that computes logp and gradient.
`InstrumentalVariableRegression.make_obs_var`(...)	Create a TensorVariable for an observed random variable.
`InstrumentalVariableRegression.name_for`(name)	Checks if name has prefix and adds if needed
`InstrumentalVariableRegression.name_of`(name)	Checks if name has prefix and deletes if needed
`InstrumentalVariableRegression.point_logps`([...])	Computes the log probability of point for all random variables in the model.
`InstrumentalVariableRegression.predict`(X)	Predict data given input data X
`InstrumentalVariableRegression.print_coefficients`(labels)
`InstrumentalVariableRegression.profile`(outs, *)	Compiles and profiles an PyTensor function which returns `outs` and takes values of model vars as a dict as an argument.
`InstrumentalVariableRegression.register_data_var`(data)	Register a data variable with the model.
`InstrumentalVariableRegression.register_rv`(...)	Register an (un)observed random variable with the model.
`InstrumentalVariableRegression.replace_rvs_by_values`(...)	Clone and replace random variables in graphs with their value variables.
`InstrumentalVariableRegression.sample_predictive_distribution`([...])	Function to sample the Multivariate Normal posterior predictive Likelihood term in the IV class.
`InstrumentalVariableRegression.score`(X, y)	Score the Bayesian \(R^2\) given inputs `X` and outputs `y`.
`InstrumentalVariableRegression.set_data`(...)	Changes the values of a data variable in the model.
`InstrumentalVariableRegression.set_dim`(name, ...)	Update a mutable dimension.
`InstrumentalVariableRegression.set_initval`(...)	Sets an initial value (strategy) for a random variable.
`InstrumentalVariableRegression.shape_from_dims`(dims)
`InstrumentalVariableRegression.to_graphviz`(*)	Produce a graphviz Digraph from a PyMC model.
`InstrumentalVariableRegression.update_start_vals`(a, b)	Update point a with b, without overwriting existing keys.

Attributes

`basic_RVs`	List of random variables the model is defined in terms of (which excludes deterministics).
`continuous_value_vars`	All the continuous value variables in the model
`coords`	Coordinate values for model dimensions.
`datalogp`	PyTensor scalar of log-probability of the observed variables and potential terms
`dim_lengths`	The symbolic lengths of dimensions in the model.
`discrete_value_vars`	All the discrete value variables in the model
`isroot`
`observedlogp`	PyTensor scalar of log-probability of the observed variables
`parent`
`potentiallogp`	PyTensor scalar of log-probability of the Potential terms
`prefix`
`root`
`unobserved_RVs`	List of all random variables, including deterministic ones.
`unobserved_value_vars`	List of all random variables (including untransformed projections), as well as deterministics used as inputs and outputs of the model's log-likelihood graph
`value_vars`	List of unobserved random variables used as inputs to the model's log-likelihood (which excludes deterministics).
`varlogp`	PyTensor scalar of log-probability of the unobserved random variables (excluding deterministic).
`varlogp_nojac`	PyTensor scalar of log-probability of the unobserved random variables (excluding deterministic) without jacobian term.

__init__(sample_kwargs=None)#

Parameters:: sample_kwargs (Optional[Dict[str, Any]]) – A dictionary of kwargs that get unpacked and passed to the pymc.sample() function. Defaults to an empty dictionary.

static __new__(cls, *args, model=UNSET, **kwargs)#

Parameters:: model (Literal[UNSET] | None | ~pymc.model.core.Model)