Wald (single-instrument) estimator — morie_iv

\(\hat\beta = (\bar y_{z=1} - \bar y_{z=0}) / (\bar d_{z=1} - \bar d_{z=0})\).

Usage

morie_iv_wald(data, outcome, treatment, instrument, alpha = 0.05)

Arguments

data: Data frame.
outcome: Outcome column.
treatment: Endogenous treatment column.
instrument: Binary instrument column.
alpha: Significance level.

Value

A named list with elements coefficients, std_errors, t_stats, p_values, ci_lower, ci_upper, variable_names, n_obs, method, details.

Examples

set.seed(11)
n <- 2000
z <- rbinom(n, 1, 0.5)
type <- sample(c("at", "nt", "co"), n, replace = TRUE, prob = c(0.1, 0.1, 0.8))
d <- ifelse(type == "at", 1L, ifelse(type == "nt", 0L, z))
y <- 0.5 + 2 * d + rnorm(n)
df <- data.frame(y, d, z)
res <- morie_iv_wald(df, outcome = "y", treatment = "d", instrument = "z")
res$coefficients["LATE"]
#>     LATE 
#> 2.158379