compute_scaling_fn: Compute item-level IRT scaling functions

In aiDIF: Differential Item Functioning for AI-Scored Assessments

Compute item-level IRT scaling functions

Description

For each item, computes a standardised difference between group parameter estimates. The result is a vector y whose robust location is estimated by estimate_robust_scale.

Usage

compute_scaling_fn(mle, type = "intercept", scale_by = "pooled")

Arguments

mle	A validated mle list (output of read_ai_scored or constructed manually). Must contain est$group.1, est$group.2 and matching var.cov matrices.
type	One of "intercept" (default) or "slope". Determines which parameters are compared.
scale_by	One of "pooled" (default), "ref", or "focal". Controls the denominator used to standardise intercept differences: "pooled" uses \sqrt{(a_1^2+a_2^2)/2}; "ref" uses a_1; "focal" uses a_2. Ignored when type = "slope".

Value

A named numeric vector of scaling-function values, one entry per item threshold (or per item for slopes).

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