# 4. Explore confounding parameter space
set.seed(2)
pars <- list(beta = 0.3, alpha = 0.6, c = 0)
n_values <- c(500, 1000, 2000)
n_sims <- 50 # Increase for more precise probabilities
ux <- seq(-2, 2, by = 0.25)
uy <- seq(-2, 2, by = 0.25)
grid <- expand.grid(u_x = ux, u_y = uy)
summarise_estimates <- function(est, beta_true) {
na_real <- as.numeric(NA)
med_null <- est["p_med", ] >= 0.05
med_wrong <- est["p_med", ] < 0.05 & est["beta_med", ] * beta_true < 0
med_bad <- med_null | med_wrong
iv_right_sign <- est["beta_iv", ] * beta_true > 0
c(
fn_med = mean(med_null),
fn_iv = mean(est["p_iv", ] >= 0.05),
wrong_sign_med = mean(med_wrong),
mean_beta_med = mean(est["beta_med", ]),
frac_med_bad = mean(med_bad),
# Conditional sign accuracy of MR/IV
frac_iv_right_given_med_bad = if (sum(med_bad) == 0) na_real else mean(iv_right_sign[med_bad]),
frac_iv_right_given_med_null = if (sum(med_null) == 0) na_real else mean(iv_right_sign[med_null]),
frac_iv_right_given_med_wrong = if (sum(med_wrong) == 0) na_real else mean(iv_right_sign[med_wrong]),
# Store counts so we can pool across grid points later
n_med_bad = sum(med_bad),
n_iv_right_med_bad = sum(iv_right_sign & med_bad),
n_med_null = sum(med_null),
n_iv_right_med_null = sum(iv_right_sign & med_null),
n_med_wrong = sum(med_wrong),
n_iv_right_med_wrong = sum(iv_right_sign & med_wrong)
)
}
simulate_grid_for_n <- function(n, grid, n_sims, pars) {
out <- matrix(NA_real_, nrow(grid), 14)
colnames(out) <- c(
"fn_med",
"fn_iv",
"wrong_sign_med",
"mean_beta_med",
"frac_med_bad",
"frac_iv_right_given_med_bad",
"frac_iv_right_given_med_null",
"frac_iv_right_given_med_wrong",
"n_med_bad",
"n_iv_right_med_bad",
"n_med_null",
"n_iv_right_med_null",
"n_med_wrong",
"n_iv_right_med_wrong"
)
for (i in seq_len(nrow(grid))) {
est <- replicate(n_sims, estimate(
dgp(
n = n,
beta = pars$beta,
alpha = pars$alpha,
c = pars$c,
u_x = grid$u_x[i],
u_y = grid$u_y[i]
)
))
out[i, ] <- summarise_estimates(est, beta_true = pars$beta)
}
cbind(
data.frame(n = n, u_x = grid$u_x, u_y = grid$u_y),
as.data.frame(out)
)
}
grid_by_n <- do.call(
rbind,
lapply(n_values, simulate_grid_for_n,
grid = grid, n_sims = n_sims, pars = pars)
)
# 5. Visualise how sample size affects MR sign accuracy
cols <- colorRampPalette(c("white", "gold", "firebrick"))(100)
op <- par(mfrow = c(1, length(n_values)))
for (n in n_values) {
n_i <- n
gsub <- subset(grid_by_n, n == n_i)
z <- matrix(gsub$frac_iv_right_given_med_bad, nrow = length(ux))
image(
ux, uy, z,
col = cols, zlim = c(0, 1),
xlab = "u_x", ylab = "u_y",
main = paste0(
"MR right sign | mediation null/wrong\n(n = ",
n,
")"
)
)
# Black curve: population mediation estimate = 0
contour(
ux, uy,
outer(ux, uy, function(a, b) pars$beta + a * b / (1 + a^2)),
levels = 0, add = TRUE,
drawlabels = FALSE, lwd = 2
)
}