doubleml.DoubleMLPLIV¶
- class doubleml.DoubleMLPLIV(obj_dml_data, ml_g, ml_m, ml_r, n_folds=5, n_rep=1, score='partialling out', dml_procedure='dml2', draw_sample_splitting=True, apply_cross_fitting=True)¶
Double machine learning for partially linear IV regression models
- Parameters
obj_dml_data (
DoubleMLData
object) – TheDoubleMLData
object providing the data and specifying the variables for the causal model.ml_g (estimator implementing
fit()
andpredict()
) – A machine learner implementingfit()
andpredict()
methods (e.g.sklearn.ensemble.RandomForestRegressor
) for the nuisance function \(g_0(X) = E[Y|X]\).ml_m (estimator implementing
fit()
andpredict()
) – A machine learner implementingfit()
andpredict()
methods (e.g.sklearn.ensemble.RandomForestRegressor
) for the nuisance function \(m_0(X) = E[Z|X]\).ml_r (estimator implementing
fit()
andpredict()
) – A machine learner implementingfit()
andpredict()
methods (e.g.sklearn.ensemble.RandomForestRegressor
) for the nuisance function \(r_0(X) = E[D|X]\).n_folds (int) – Number of folds. Default is
5
.n_rep (int) – Number of repetitons for the sample splitting. Default is
1
.score (str or callable) – A str (
'partialling out'
is the only choice) specifying the score function or a callable object / function with signaturepsi_a, psi_b = score(y, z, d, g_hat, m_hat, r_hat, smpls)
. Default is'partialling out'
.dml_procedure (str) – A str (
'dml1'
or'dml2'
) specifying the double machine learning algorithm. Default is'dml2'
.draw_sample_splitting (bool) – Indicates whether the sample splitting should be drawn during initialization of the object. Default is
True
.apply_cross_fitting (bool) – Indicates whether cross-fitting should be applied. Default is
True
.
Examples
>>> import numpy as np >>> import doubleml as dml >>> from doubleml.datasets import make_pliv_CHS2015 >>> from sklearn.ensemble import RandomForestRegressor >>> from sklearn.base import clone >>> np.random.seed(3141) >>> learner = RandomForestRegressor(n_estimators=100, max_features=20, max_depth=5, min_samples_leaf=2) >>> ml_g = clone(learner) >>> ml_m = clone(learner) >>> ml_r = clone(learner) >>> data = make_pliv_CHS2015(alpha=0.5, n_obs=500, dim_x=20, dim_z=1, return_type='DataFrame') >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd', z_cols='Z1') >>> dml_pliv_obj = dml.DoubleMLPLIV(obj_dml_data, ml_g, ml_m, ml_r) >>> dml_pliv_obj.fit().summary coef std err t P>|t| 2.5 % 97.5 % d 0.522753 0.082263 6.354688 2.088504e-10 0.361521 0.683984
Notes
Partially linear IV regression (PLIV) models take the form
\[ \begin{align}\begin{aligned}Y - D \theta_0 = g_0(X) + \zeta, & &\mathbb{E}(\zeta | Z, X) = 0,\\Z = m_0(X) + V, & &\mathbb{E}(V | X) = 0.\end{aligned}\end{align} \]where \(Y\) is the outcome variable, \(D\) is the policy variable of interest and \(Z\) denotes one or multiple instrumental variables. The high-dimensional vector \(X = (X_1, \ldots, X_p)\) consists of other confounding covariates, and \(\zeta\) and \(V\) are stochastic errors.
Methods
bootstrap
([method, n_rep_boot])Multiplier bootstrap for DoubleML models.
confint
([joint, level])Confidence intervals for DoubleML models.
Draw sample splitting for DoubleML models.
fit
([n_jobs_cv, keep_scores, store_predictions])Estimate DoubleML models.
get_params
(learner)Get hyperparameters for the nuisance model of DoubleML models.
p_adjust
([method])Multiple testing adjustment for DoubleML models.
set_ml_nuisance_params
(learner, treat_var, …)Set hyperparameters for the nuisance models of DoubleML models.
set_sample_splitting
(all_smpls)Set the sample splitting for DoubleML models.
tune
(param_grids[, tune_on_folds, …])Hyperparameter-tuning for DoubleML models.
Attributes
all_coef
Estimates of the causal parameter(s) for the
n_rep
different sample splits after callingfit()
.all_dml1_coef
Estimates of the causal parameter(s) for the
n_rep
xn_folds
different folds after callingfit()
withdml_procedure='dml1'
.all_se
Standard errors of the causal parameter(s) for the
n_rep
different sample splits after callingfit()
.apply_cross_fitting
Indicates whether cross-fitting should be applied.
boot_coef
Bootstrapped coefficients for the causal parameter(s) after calling
fit()
andbootstrap()
.boot_t_stat
Bootstrapped t-statistics for the causal parameter(s) after calling
fit()
andbootstrap()
.coef
Estimates for the causal parameter(s) after calling
fit()
.dml_procedure
The double machine learning algorithm.
learner
The machine learners for the nuisance functions.
learner_names
The names of the learners.
n_folds
Number of folds.
n_rep
Number of repetitions for the sample splitting.
n_rep_boot
The number of bootstrap replications.
params
The hyperparameters of the learners.
params_names
The names of the nuisance models with hyperparameters.
predictions
The predictions of the nuisance models.
psi
Values of the score function \(\psi(W; \theta, \eta) = \psi_a(W; \eta) \theta + \psi_b(W; \eta)\) after calling
fit()
.psi_a
Values of the score function component \(\psi_a(W; \eta)\) after calling
fit()
.psi_b
Values of the score function component \(\psi_b(W; \eta)\) after calling
fit()
.pval
p-values for the causal parameter(s) after calling
fit()
.score
The score function.
se
Standard errors for the causal parameter(s) after calling
fit()
.smpls
The partition used for cross-fitting.
summary
A summary for the estimated causal effect after calling
fit()
.t_stat
t-statistics for the causal parameter(s) after calling
fit()
.
- DoubleMLPLIV.bootstrap(method='normal', n_rep_boot=500)¶
Multiplier bootstrap for DoubleML models.
- DoubleMLPLIV.confint(joint=False, level=0.95)¶
Confidence intervals for DoubleML models.
- DoubleMLPLIV.draw_sample_splitting()¶
Draw sample splitting for DoubleML models.
The samples are drawn according to the attributes
n_folds
,n_rep
andapply_cross_fitting
.- Returns
self
- Return type
- DoubleMLPLIV.fit(n_jobs_cv=None, keep_scores=True, store_predictions=False)¶
Estimate DoubleML models.
- Parameters
n_jobs_cv (None or int) – The number of CPUs to use to fit the learners.
None
means1
. Default isNone
.keep_scores (bool) – Indicates whether the score function evaluations should be stored in
psi
,psi_a
andpsi_b
. Default isTrue
.store_predictions (bool) – Indicates whether the predictions for the nuisance functions should be be stored in
predictions
. Default isFalse
.
- Returns
self
- Return type
- DoubleMLPLIV.get_params(learner)¶
Get hyperparameters for the nuisance model of DoubleML models.
- DoubleMLPLIV.p_adjust(method='romano-wolf')¶
Multiple testing adjustment for DoubleML models.
- Parameters
method (str) – A str (
'romano-wolf''
,'bonferroni'
,'holm'
, etc) specifying the adjustment method. In addition to'romano-wolf''
, all methods implemented instatsmodels.stats.multitest.multipletests()
can be applied. Default is'romano-wolf'
.- Returns
p_val – A data frame with adjusted p-values.
- Return type
pd.DataFrame
- DoubleMLPLIV.set_ml_nuisance_params(learner, treat_var, params)¶
Set hyperparameters for the nuisance models of DoubleML models.
- Parameters
learner (str) – The nuisance model / learner (see attribute
params_names
).treat_var (str) – The treatment variable (hyperparameters can be set treatment-variable specific).
params (dict or list) – A dict with estimator parameters (used for all folds) or a nested list with fold specific parameters. The outer list needs to be of length
n_rep
and the inner list of lengthn_folds
.
- Returns
self
- Return type
- DoubleMLPLIV.set_sample_splitting(all_smpls)¶
Set the sample splitting for DoubleML models.
The attributes
n_folds
andn_rep
are derived from the provided partition.- Parameters
- If nested list of lists of tuples:
The outer list needs to provide an entry per repeated sample splitting (length of list is set as
n_rep
). The inner list needs to provide a tuple (train_ind, test_ind) per fold (length of list is set asn_folds
). If tuples for more than one fold are provided, it must form a partition andapply_cross_fitting
is set to True. Otherwiseapply_cross_fitting
is set to False andn_folds=2
.- If list of tuples:
The list needs to provide a tuple (train_ind, test_ind) per fold (length of list is set as
n_folds
). If tuples for more than one fold are provided, it must form a partition andapply_cross_fitting
is set to True. Otherwiseapply_cross_fitting
is set to False andn_folds=2
.n_rep=1
is always set.- If tuple:
Must be a tuple with two elements train_ind and test_ind. No sample splitting is achieved if train_ind and test_ind are range(n_rep). Otherwise
n_folds=2
.apply_cross_fitting=False
andn_rep=1
is always set.
- Returns
self
- Return type
Examples
>>> import numpy as np >>> import doubleml as dml >>> from doubleml.datasets import make_plr_CCDDHNR2018 >>> from sklearn.ensemble import RandomForestRegressor >>> from sklearn.base import clone >>> np.random.seed(3141) >>> learner = RandomForestRegressor(max_depth=2, n_estimators=10) >>> ml_g = learner >>> ml_m = learner >>> obj_dml_data = make_plr_CCDDHNR2018(n_obs=10, alpha=0.5) >>> dml_plr_obj = dml.DoubleMLPLR(obj_dml_data, ml_g, ml_m) >>> # simple sample splitting with two folds and without cross-fitting >>> smpls = ([0, 1, 2, 3, 4], [5, 6, 7, 8, 9]) >>> dml_plr_obj.set_sample_splitting(smpls) >>> # sample splitting with two folds and cross-fitting >>> smpls = [([0, 1, 2, 3, 4], [5, 6, 7, 8, 9]), >>> ([5, 6, 7, 8, 9], [0, 1, 2, 3, 4])] >>> dml_plr_obj.set_sample_splitting(smpls) >>> # sample splitting with two folds and repeated cross-fitting with n_rep = 2 >>> smpls = [[([0, 1, 2, 3, 4], [5, 6, 7, 8, 9]), >>> ([5, 6, 7, 8, 9], [0, 1, 2, 3, 4])], >>> [([0, 2, 4, 6, 8], [1, 3, 5, 7, 9]), >>> ([1, 3, 5, 7, 9], [0, 2, 4, 6, 8])]] >>> dml_plr_obj.set_sample_splitting(smpls)
- DoubleMLPLIV.tune(param_grids, tune_on_folds=False, scoring_methods=None, n_folds_tune=5, search_mode='grid_search', n_iter_randomized_search=100, n_jobs_cv=None, set_as_params=True, return_tune_res=False)¶
Hyperparameter-tuning for DoubleML models.
The hyperparameter-tuning is performed using either an exhaustive search over specified parameter values implemented in
sklearn.model_selection.GridSearchCV
or via a randomized search implemented insklearn.model_selection.RandomizedSearchCV
.- Parameters
param_grids (dict) – A dict with a parameter grid for each nuisance model / learner (see attribute
learner_names
).tune_on_folds (bool) – Indicates whether the tuning should be done fold-specific or globally. Default is
False
.scoring_methods (None or dict) – The scoring method used to evaluate the predictions. The scoring method must be set per nuisance model via a dict (see attribute
learner_names
for the keys). If None, the estimator’s score method is used. Default isNone
.n_folds_tune (int) – Number of folds used for tuning. Default is
5
.search_mode (str) – A str (
'grid_search'
or'randomized_search'
) specifying whether hyperparameters are optimized viasklearn.model_selection.GridSearchCV
orsklearn.model_selection.RandomizedSearchCV
. Default is'grid_search'
.n_iter_randomized_search (int) – If
search_mode == 'randomized_search'
. The number of parameter settings that are sampled. Default is100
.n_jobs_cv (None or int) – The number of CPUs to use to tune the learners.
None
means1
. Default isNone
.set_as_params (bool) – Indicates whether the hyperparameters should be set in order to be used when
fit()
is called. Default isTrue
.return_tune_res (bool) – Indicates whether detailed tuning results should be returned. Default is
False
.
- Returns
self (object) – Returned if
return_tune_res
isFalse
.tune_res (list) – A list containing detailed tuning results and the proposed hyperparameters. Returned if
return_tune_res
isFalse
.