DPI: The Directed Prediction Index

The Directed Prediction Index ('DPI') is a simulation-based method for quantifying the relative endogeneity (relative dependence) of outcome (Y) versus predictor (X) variables in multiple linear regression models. By comparing the proportion of variance explained (R-squared) between the Y-as-outcome model and the X-as-outcome model while controlling for a sufficient number of potential confounding variables, it suggests a more plausible influence direction from a more exogenous variable (X) to a more endogenous variable (Y). Methodological details are provided at <https://psychbruce.github.io/DPI/>.

Version: 2025.8
Depends: R (≥ 4.0.0)
Imports: glue, crayon, cli, ggplot2, cowplot, qgraph, bnlearn
Suggests: bruceR
Published: 2025-08-20
DOI: 10.32614/CRAN.package.DPI
Author: Han Wu Shuang Bao ORCID iD [aut, cre]
Maintainer: Han Wu Shuang Bao <baohws at foxmail.com>
BugReports: https://github.com/psychbruce/DPI/issues
License: GPL-3
URL: https://psychbruce.github.io/DPI/
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: DPI results

Documentation:

Reference manual: DPI.html , DPI.pdf

Downloads:

Package source: DPI_2025.8.tar.gz
Windows binaries: r-devel: DPI_2025.8.zip, r-release: DPI_2025.6.zip, r-oldrel: DPI_2025.6.zip
macOS binaries: r-release (arm64): DPI_2025.8.tgz, r-oldrel (arm64): DPI_2025.6.tgz, r-release (x86_64): DPI_2025.8.tgz, r-oldrel (x86_64): DPI_2025.8.tgz
Old sources: DPI archive

Linking:

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