Skip to contents

Two-step efficient GMM via gmm::gmm; falls back to 2SLS otherwise.

Usage

morie_iv_gmm(
  data,
  outcome,
  endogenous,
  instruments,
  exogenous = NULL,
  weight_matrix = "optimal",
  robust = TRUE,
  alpha = 0.05
)

Arguments

data

Data frame.

outcome

Name of the outcome column.

endogenous

Character vector of endogenous regressor names.

instruments

Character vector of excluded-instrument names.

exogenous

Optional character vector of exogenous covariate names.

weight_matrix

One of "optimal" (default, two-step) or "identity" (one-step / 2SLS-equivalent).

robust

Logical; if TRUE use HC1 robust standard errors.

alpha

Significance level for confidence intervals.