statsmodels.sandbox.regression.gmm.IV2SLS

class statsmodels.sandbox.regression.gmm.IV2SLS(endog, exog, instrument=None)

Instrumental variables estimation using Two-Stage Least-Squares (2SLS)

Parameters:

endogndarray

Endogenous variable, 1-dimensional or 2-dimensional array nobs by 1

exogndarray

Explanatory variables, 1-dimensional or 2-dimensional array nobs by k

instrumentndarray

Instruments for explanatory variables. Must contain both exog variables that are not being instrumented and instruments

Attributes:

endog_names

Names of endogenous variables

exog_names

Names of exogenous variables

Methods

fit()	estimate model using 2SLS IV regression
from_formula(formula, data[, subset, drop_cols])	Create a Model from a formula and dataframe
hessian(params)	The Hessian matrix of the model
information(params)	Fisher information matrix of model
initialize()	Initialize (possibly re-initialize) a Model instance
loglike(params)	Log-likelihood of model
predict(params[, exog])	Return linear predicted values from a design matrix.
score(params)	Score vector of model
whiten(X)	Not implemented

Notes

All variables in exog are instrumented in the calculations. If variables in exog are not supposed to be instrumented, then these variables must also to be included in the instrument array.

Degrees of freedom in the calculation of the standard errors uses df_resid = (nobs - k_vars). (This corresponds to the small option in Stata’s ivreg2.)

Methods

fit()	estimate model using 2SLS IV regression
from_formula(formula, data[, subset, drop_cols])	Create a Model from a formula and dataframe
hessian(params)	The Hessian matrix of the model
information(params)	Fisher information matrix of model
initialize()	Initialize (possibly re-initialize) a Model instance
loglike(params)	Log-likelihood of model
predict(params[, exog])	Return linear predicted values from a design matrix.
score(params)	Score vector of model
whiten(X)	Not implemented

Properties

endog_names	Names of endogenous variables
exog_names	Names of exogenous variables