grad_intercept_fn: Gradient of the intercept scaling function

In aiDIF: Differential Item Functioning for AI-Scored Assessments

Gradient of the intercept scaling function

Description

Computes the Jacobian of compute_scaling_fn with respect to all item parameters in both groups, organised to be conformable with the block-diagonal covariance matrix built by build_joint_vcov.

Usage

grad_intercept_fn(mle, theta = NULL, scale_by = "pooled")

Arguments

mle	A validated mle list.
theta	Optional scalar: if supplied, item-specific scaling-function values are replaced by theta in the gradient (used when evaluating under H0).
scale_by	Passed from compute_scaling_fn.

Value

A matrix with n_items * n_thresholds columns, each being the gradient vector of one scaling-function entry with respect to the full parameter vector.

aiDIF documentation built on April 22, 2026, 1:10 a.m.