Function qq_plot_data 

pub fn qq_plot_data(residuals: ArrayView1<'_, f64>) -> Vec<(f64, f64)>

Theoretical-vs-sample quantile pairs for a normal QQ plot of residuals.

For sorted residuals, observation i (1-indexed) is paired with the standard normal quantile at plotting position (i − 0.5) / n. The returned pairs are (theoretical_quantile, sample_quantile), sorted ascending by sample value — ready to scatter.

This crate produces the data, not the rendering. The natural pairing is with plotters-statistical’s scatter/reference-line primitives: a straight diagonal (y = x) is the “perfect normality” baseline, conceptually the same role its RocCurve diagonal plays. That is a documented cross-crate integration point, not a hard dependency — pass the pairs into any plotting backend you like.

Typically you feed in standardized or studentized residuals so the diagonal reference line has unit slope; raw residuals produce a line whose slope is the residual standard deviation.

Example

use ndarray::array;
use regression_diagnostics::residuals::qq_plot_data;

let r = array![-1.2, 0.3, -0.1, 0.9, 0.05];
let pairs = qq_plot_data(r.view());
assert_eq!(pairs.len(), 5);
// Sample quantiles come out sorted ascending.
assert!(pairs.windows(2).all(|w| w[0].1 <= w[1].1));