DPI-package

<img src="figures/logo.png?package=DPI&version=2025.11" style="float: right" alt="logo" width="120">
The Directed Prediction Index ('DPI') is a quasi-causal inference (causal discovery) method for observational data designed to quantify the relative endogeneity (relative dependence) of outcome (Y) versus predictor (X) variables in 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 possible confounders, it can suggest a plausible (admissible) direction of influence from a less endogenous variable (X) to a more endogenous variable (Y). Methodological details are provided at <a href="https://psychbruce.github.io/DPI/">https://psychbruce.github.io/DPI/</a>. This package also includes functions for data simulation and network analysis (correlation, partial correlation, and Bayesian networks).

internal

The Directed Prediction Index ('DPI') is
a quasi-causal inference (causal discovery) method for observational data
designed to quantify the relative endogeneity (relative dependence)
of outcome (Y) versus predictor (X) variables in 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 possible confounders,
it can suggest a plausible (admissible) direction of influence
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).

Han-Wu-Shuang Bao

The Directed Prediction Index for Causal Direction Inference
from Observational Data

DPI-package function

Maintainer: Han Wu Shuang Bao <a href="/link/baohws%40foxmail.com?package=DPI&version=2025.11" data-mini-rdoc="DPI::baohws@foxmail.com">baohws@foxmail.com</a> (<a href="https://orcid.org/0000-0003-3043-710X">ORCID</a>)

Author

<img src='figures/logo.png' style='float: right' alt='logo' width='120' />
The Directed Prediction Index ('DPI') is a quasi-causal inference (causal discovery) method for observational data designed to quantify the relative endogeneity (relative dependence) of outcome (Y) versus predictor (X) variables in 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 possible confounders, it can suggest a plausible (admissible) direction of influence from a less endogenous variable (X) to a more endogenous variable (Y). Methodological details are provided at <a href='https://psychbruce.github.io/DPI/'>https://psychbruce.github.io/DPI/</a>. This package also includes functions for data simulation and network analysis (correlation, partial correlation, and Bayesian networks).

DPI: The Directed Prediction Index for Causal Direction Inference from Observational Data — DPI-package

Maintainer: Han Wu Shuang Bao <a href='mailto:baohws@foxmail.com'>baohws@foxmail.com</a> (<a href='https://orcid.org/0000-0003-3043-710X'>ORCID</a>)

DPI-package: DPI: The Directed Prediction Index for Causal Direction Inference from Observational Data

Description

Arguments

Author

See Also