// dgp_irm.mbt
//
// Pure-MoonBit port of upstream
// `doubleml.irm.datasets.dgp_irm_data.make_irm_data`.
//
// IRM (Interactive Regression Model) data generating process from
// Chernozhukov et al. (2018) "Double/debiased machine learning for
// treatment and structural parameters", Econometrics Journal 21:
// C1-C68, Section 4.2. Same partially-linear structure as the PLR
// DGP, but with binary treatment `d` drawn from a logistic
// propensity:
//
// p_i = sigmoid(0.5 * x_{i,1} + 0.5 * x_{i,2}),
// d_i ~ Bernoulli(p_i),
//
// y_i = theta * d_i + 0.5 * sigmoid(x_{i,1})
// + 0.5 * sigmoid(x_{i,2}) + v_i,
// v_i ~ N(0, 1),
//
// X ~ N(0, Sigma), Sigma_{kj} = 0.7^|j-k|.
//
// The true causal parameter is theta (default 0.5). The MoonBit
// port omits the upstream `return_type` parameter
// (DataFrame/DoubleMLData/tuple).
///|
/// Result of the IRM DGP.
struct IrmData {
/// Causal parameter used in `y = theta * d + g(X) + noise`.
theta : Double
/// `Matrix` of shape `(n_obs, dim_x)`.
x : Matrix
/// Outcome vector of length `n_obs`.
y : Array[Double]
/// Binary treatment vector of length `n_obs` (0.0 or 1.0).
d : Array[Double]
}
///|
/// Generate the IRM DGP from Chernozhukov et al. (2018) Section 4.2.
pub fn make_irm_data(
n_obs : Int,
dim_x : Int,
theta : Double,
seed : Int,
) -> IrmData {
let rng = chacha8_rng(seed)
// 1. Pre-draw n_obs * dim_x standard normals via Box-Muller.
let n_normals_x = n_obs * dim_x
let z_flat : Array[Double] = Array::make(n_normals_x, 0.0)
let half_z = (n_normals_x + 1) / 2
for i = 0; i < half_z; i = i + 1 {
let (z1, z2) = box_muller_pair(rng)
let idx_a = 2 * i
let idx_b = 2 * i + 1
if idx_a < n_normals_x {
z_flat[idx_a] = z1
}
if idx_b < n_normals_x {
z_flat[idx_b] = z2
}
}
// 2. Build X ~ N(0, Sigma) via lower-triangular L.
let x_flat : Array[Double] = Array::make(n_normals_x, 0.0)
for i = 0; i < n_obs; i = i + 1 {
for k = 0; k < dim_x; k = k + 1 {
let mut s = 0.0
let mut acc = 1.0
let mut j = k
while j >= 0 {
s = s + acc * z_flat[i * dim_x + j]
acc = acc * 0.7
if j == 0 {
break
}
j = j - 1
}
x_flat[i * dim_x + k] = s
}
}
// 3. Pre-draw v ~ N(0, 1) (for the outcome noise).
let v_flat : Array[Double] = Array::make(n_obs, 0.0)
let half_n = (n_obs + 1) / 2
for i = 0; i < half_n; i = i + 1 {
let (z1, z2) = box_muller_pair(rng)
let idx_a = 2 * i
let idx_b = 2 * i + 1
if idx_a < n_obs {
v_flat[idx_a] = z1
}
if idx_b < n_obs {
v_flat[idx_b] = z2
}
}
// 4. Build d (binary) and y per the IRM DGP formula.
let d : Array[Double] = Array::make(n_obs, 0.0)
let y : Array[Double] = Array::make(n_obs, 0.0)
for i = 0; i < n_obs; i = i + 1 {
let x1 = x_flat[i * dim_x + 1]
let x2 = x_flat[i * dim_x + 2]
let p_score = 0.5 * x1 + 0.5 * x2
let p = 1.0 / (1.0 + @math.exp(-p_score))
d[i] = if rng.double() < p { 1.0 } else { 0.0 }
let sig1 = 1.0 / (1.0 + @math.exp(-x1))
let sig2 = 1.0 / (1.0 + @math.exp(-x2))
y[i] = theta * d[i] + 0.5 * sig1 + 0.5 * sig2 + v_flat[i]
}
let x_mat = Matrix::from_array(x_flat, n_obs, dim_x)
{ theta, x: x_mat, y, d }
}
///|
/// Get the causal parameter (theta).
pub fn IrmData::theta_get(self : IrmData) -> Double {
self.theta
}
///|
/// Get the design matrix.
pub fn IrmData::x_get(self : IrmData) -> Matrix {
self.x
}
///|
/// Get the outcome vector.
pub fn IrmData::y_get(self : IrmData) -> Array[Double] {
self.y
}
///|
/// Get the binary treatment vector.
pub fn IrmData::d_get(self : IrmData) -> Array[Double] {
self.d
}