LMDT: Local Manifold Dispersion Test for Heteroskedasticity

Implements the Local Manifold Dispersion Test (LMDT) for detecting complex, non-linear, and high-dimensional heteroskedasticity in linear regression models. LMDT measures the spectral smoothness (Dirichlet energy) of robust log-dispersion residuals over a self-tuning k-nearest neighbors graph Laplacian, as formulated in Jabbar (2026). The test statistic is asymptotically distribution-free with respect to error kurtosis and accommodates high-dimensional covariates (p > 50) via Gavish-Donoho optimal hard thresholding and supervised metric learning.

Version:	0.1.0
Depends:	R (≥ 4.0.0)
Imports:	stats
Suggests:	testthat (≥ 3.0.0), knitr, rmarkdown
Published:	2026-10-24
DOI:	10.32614/CRAN.package.LMDT
Author:	Ahmed Sattar Jabbar [aut, cre]
Maintainer:	Ahmed Sattar Jabbar <ahmed.state.me at gmail.com>
BugReports:	https://github.com/amjed-droid/LMDT/issues
License:	GPL (≥ 3)
URL:	https://amjed-droid.github.io/LMDT/, https://github.com/amjed-droid/LMDT
NeedsCompilation:	no
Citation:	LMDT citation info
Materials:	README, NEWS
CRAN checks:	LMDT results

Documentation:

Reference manual:	LMDT.html , LMDT.pdf
Vignettes:	Empirical Econometric Applications of the Local Manifold Dispersion Test (LMDT) (source, R code)

Downloads:

Package source:	LMDT_0.1.0.tar.gz
Windows binaries:	r-devel: LMDT_0.1.0.zip, r-release: LMDT_0.1.0.zip, r-oldrel: LMDT_0.1.0.zip
macOS binaries:	r-release (arm64): LMDT_0.1.0.tgz, r-oldrel (arm64): LMDT_0.1.0.tgz, r-release (x86_64): LMDT_0.1.0.tgz, r-oldrel (x86_64): LMDT_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=LMDT to link to this page.