linearmodels.iv.model.IVGMMCUE¶

class linearmodels.iv.model.IVGMMCUE(dependent, exog, endog, instruments, *, weights=None, weight_type='robust', **weight_config)[source]¶

Estimation of IV models using continuously updating GMM

Parameters:¶

dependent : array_like¶

Endogenous variables (nobs by 1)

exog : array_like¶

Exogenous regressors (nobs by nexog)

endog : array_like¶

Endogenous regressors (nobs by nendog)

instruments : array_like¶

Instrumental variables (nobs by ninstr)

weights : array_like¶

Observation weights used in estimation

weight_type : str¶

Name of moment condition weight function to use in the GMM estimation

**weight_config : Any

Additional keyword arguments to pass to the moment condition weight function

Notes

Available weight functions are:

• “unadjusted”, “homoskedastic” - Assumes moment conditions are homoskedastic

• “robust”, “heteroskedastic” - Allows for heteroskedasticity by not autocorrelation

• “kernel” - Allows for heteroskedasticity and autocorrelation

• “cluster” - Allows for one-way cluster dependence

In most circumstances, the center weight option should be True to avoid starting value dependence.

\[\begin{split}\hat{\beta}_{cue} & =\min_{\beta}\bar{g}(\beta)'W(\beta)^{-1}g(\beta)\\ g(\beta) & =n^{-1}\sum_{i=1}^{n}z_{i}(y_{i}-x_{i}\beta)\end{split}\]

where \(W(\beta)\) is a weight matrix that depends on \(\beta\) through \(\epsilon_i = y_i - x_i\beta\).

See also

IV2SLS, IVLIML, IVGMM

Methods

estimate_parameters(starting, x, y, z[, ...])	type starting: ndarray
fit(*[, starting, display, cov_type, ...])	Estimate model parameters
from_formula(formula, data, *[, weights, ...])	type formula: str
j(params, x, y, z)	Optimization target
predict(params, *[, exog, endog, data, eval_env])	Predict values for additional data
resids(params)	Compute model residuals
wresids(params)	Compute weighted model residuals

Properties

formula	Formula used to create the model
has_constant	Flag indicating the model includes a constant or equivalent
isnull	Locations of observations with missing values
notnull	Locations of observations included in estimation