DPI_dag() and plot.dpi.dag(). Also forced the plot to strictly show a DAG while changing edge color of insignificant DPI into faded grey.DPI_curve() for wrong (reverse) direction of DPI caused by the change of parameter order of x and y in version 2025.10.dpi parameter-object name conflict (internally) when saving DPI() results into a file.This version contains breaking changes to function names and visualization methods.
DPI_dag(): Directed acyclic graphs (DAGs) via DPI exploratory analysis (causal discovery) for all significant partial correlations.bonf and pseudoBF parameters to DPI(), DPI_curve(), and DPI_dag().
bonf: Bonferroni correction to control for false positive rates among multiple pairwise DPI tests.pseudoBF: Use normalized pseudo Bayes Factors sigmoid(log(PseudoBF10)) as the Significance score (0~1). Pseudo Bayes Factors are computed using the transformation rules proposed by Wagenmakers (2022) https://doi.org/10.31234/osf.io/egydq.plot.cor.net(), plot.bns.dag(), and plot.dpi.dag() that can transform qgraph base-plot objects into ggplot objects for more stable and flexible visualization.p_to_bf(): Convert p values to pseudo Bayes Factors ($\text{PseudoBF}_{10}$).cor_network() to cor_net(), dag_network() to BNs_dag(), and matrix_cor() to cor_matrix().cor_net() to return the exactly correct p values of (partial) correlation coefficients.This version contains breaking changes to both algorithm and functionality.
DPI() algorithm to limit $\text{DPI} \in (-1, 1)$ and also simplified its output information. $$
\begin{aligned}
\text{DPI}{X \rightarrow Y}
& = \text{Direction}{X \rightarrow Y} \cdot \text{Significance}{X \rightarrow Y} \
& = \text{Delta}(R^2) \cdot \text{Sigmoid}(\frac{p}{\alpha}) \
& = \left( R{Y \sim X + Covs}^2 - R_{X \sim Y + Covs}^2 \right) \cdot \left( 1 - \tanh \frac{p_{XY|Covs}}{2\alpha} \right) \
& \in (-1, 1)
\end{aligned}
$$
data_random() to sim_data() with enhanced functionality that supports data simulation from a multivariate normal distribution, using MASS::mvrnorm().sim_data_exp(): Simulate experiment-like data with independent binary Xs.gc() in DPI(), DPI_curve(), and dag_network() for memory garbage collection.dag_network() for arranging multiple base-R-style plots using aplot::plot_list().dag_network(): Directed acyclic graphs (DAGs) via causal Bayesian networks (BNs).cor_network(): Correlation and partial correlation networks.S3method.dpi and S3method.network and made them as internal topics.