statsmodels.sandbox.regression.gmm.LinearIVGMM.fititer¶

LinearIVGMM.fititer(start, maxiter=2, start_invweights=None, weights_method='cov', wargs=(), optim_method='bfgs', optim_args=None)¶

iterative estimation with updating of optimal weighting matrix

stopping criteria are maxiter or change in parameter estimate less than self.epsilon_iter, with default 1e-6.

Parameters:¶

start : ndarray¶

starting value for parameters

maxiter : int¶

maximum number of iterations

start_weights : array (nmoms, nmoms)

initial weighting matrix; if None, then the identity matrix is used

weights_method : {'cov', ...}¶

method to use to estimate the optimal weighting matrix, see calc_weightmatrix for details

Returns:¶

• params (ndarray) – estimated parameters

• weights (ndarray) – optimal weighting matrix calculated with final parameter estimates

Notes