The Directed Prediction Index for Causal Direction Inference from Observational Data R package DPI version 2026.2 The Directed Prediction Index ('DPI') is a causal discovery method for observational data designed to quantify the relative endogeneity of outcome (Y) versus predictor (X) variables in regression models. By comparing the coefficients of determination (R-squared) between the Y-as-outcome and X-as-outcome models while controlling for sufficient confounders and simulating k random covariates, it can quantify relative endogeneity, providing a necessary but insufficient condition for causal direction from a less endogenous variable (X) to a more endogenous variable (Y). Methodological details are provided at <https://psychbruce.github.io/DPI/>. This package also includes functions for data simulation and network analysis (correlation, partial correlation, and Bayesian Networks). Software Depends: R (>= 4.0.0) Imports: glue, crayon, cli, ggplot2, cowplot, qgraph, bnlearn, MASS Suggests: bruceR, aplot, bayestestR Han Wu Shuang Bao <baohws@foxmail.com> Comprehensive R Archive Network (CRAN) Han Wu Shuang Bao [aut, cre] (ORCID: <https://orcid.org/0000-0003-3043-710X>) GPL-3 2026-02-26 application/tgz https://CRAN.R-project.org/package=DPI doi:10.32614/CRAN.package.DPI