Handling Missing Data in Probabilistic Regression Trees

Handling Missingness and Censoring in Dirichlet Mixture Models

Incomplete compositional data analysis faces a fundamental limitation: likelihood-based methods for compositional models generally require fully observed compositions, making it difficult to accommodate missing or censored proportions directly on the simplex. Consequently, analysts often discard partially observed compositions or transform the data into unconstrained spaces, potentially sacrificing interpretability and coherence. This paper proposes a likelihood-based method for incomplete compositional data without leaving the simplex. Specifically, we develop an Expectation-Maximisation (EM) type algorithm for fitting finite mixtures of Dirichlet distributions in the presence of missing and censored components. The proposed approach performs parameter estimation and model-based imputation simultaneously while preserving the compositional structure and interpretability of the original variables. A simulation experiment evaluates the performance of the proposed estimators and imputations under increasingly complex coarsening mechanisms. Particular attention is paid to clustering performance, and model selection outcomes. The results showed beneficial clustering performance despite observations being incomplete, and a higher probability of model selection metrics identifying the correct number of clusters compared to current alternative of case-deletion. The practical utility of the method is illustrated using two real datasets with distinct coarsened patterns. Analysis of the xenolith dataset identifies a four-component Dirichlet mixture that reveals interpretable profiles of rock types and speciation methods. Application to PM$_{2.5}$ speciation data from the Air Quality System, containing both left-censored and missing-at-random values, supports a four-component mixture model that characterises compositional parts of particulate matter across the United States.

Handling Missingness and Censoring in Dirichlet Models

Likelihood-based inference for compositional data generally requires fully observed compositions, hindering the direct treatment of missing or censored components on the simplex. In this paper, we develop an expectation-maximisation (EM)-type algorithm for maximum likelihood estimation of the Dirichlet parameters in the presence of missing and censored components under a unified coarsening framework. The Dirichlet distribution---the canonical probability model for compositional data, which plays a role analogous to that of the multivariate normal distribution for unconstrained multivariate data---provides the foundation for our methodology. Our methodology preserves the compositional structure of the data while simultaneously performing parameter estimation and model-based imputation. We evaluate the performance of our estimators and imputations through a simulation study under increasingly complex coarsening mechanisms, including both missing and censored data. We compare our method with an existing model-based approach and a nonparametric alternative. Finally, we illustrate the practical utility of our methodology using mercury speciation data, in which compositions are only partially observed because of detection limits and incomplete speciation. Our results indicate that the Dirichlet distribution provides a suitable model for these data and that our method yields imputations that better preserve the observed compositional structure than competing approaches.

Not All Missing Data are Equal: Choosing the Right Imputation Method for Binary Datasets

Missing binary predictors are common in reliability, quality control, and industrial decision systems, yet imputation methods are often chosen by convenience rather than evidence. We conduct a Monte Carlo study comparing mode substitution, sequential hot‐deck, missForest, MICE, and KNN with three neighbourhood sizes under MCAR, MAR, and MNAR missingness, across missingness rates from 5% to 50% and two predictor‐dependence structures. Performance is evaluated on three targets: exact recovery of missing binary cells, recovery of logistic‐regression coefficients, and downstream classification using logistic regression, naive Bayes, support vector machines, and random forests. The results reveal a clear trade‐off. KNN is strongest for exact cell recovery under MCAR and MAR, whereas missForest performs best under MNAR. MICE is the most reliable choice for downstream predictive performance across learners and missingness mechanisms. By contrast, mode imputation and sequential hot‐deck achieve the best coefficient recovery. The main implication is operational: in binary‐data environments, imputation should be chosen to match the analytical objective–reconstruction, inference, or prediction–because no single method dominates all targets simultaneously.

A Bayesian statistical model for count data for association and prediction studies in moderate and high dimension

Bayesian model comparison for random effects probit models with missing covariates

For model comparison in random effects probit models with incompletely observed covariates, this paper develops a Bayesian data-augmentation workflow in which latent Gaussian responses, random effects, and missing covariate values are updated within a common augmented sampling scheme. Because specifying a fully parametric joint model for mixed continuous and categorical covariates is often unattractive in survey applications, missing covariates are updated by a decision-tree-assisted Bayesian-bootstrap step. Competing models are evaluated conditionally on one common medoid completion using Chib’s method with reduced Gibbs sampling; sensitivity is assessed with respect to the Chib evaluation point, the regression-coefficient prior, and the medoid reference model. The simulation study compares the proposed approach with complete case analysis, multiple imputation by chained equations, missForest single imputation, information criteria, and predictive criteria under MCAR, cross-dependent MAR-type, and self-masked MNAR scenarios. An empirical illustration based on the National Educational Panel Study demonstrates how the method can be used for comparing labor-market models of current employment when competence measures and employment-history covariates are incompletely observed. The results show that missing covariates can materially affect model rankings, and that the proposed workflow provides a transparent evidence-based comparison of nested and non-nested random effects probit specifications under incomplete covariate information.

Distributional Split Criteria for Random Forests: Extensions, Shrinkage, and the Robustness of Mean Splitting

Distributional random forests replace mean-based CART splitting with criteria that compare the full conditional response distribution in candidate children. We implement and systematically study a family of such criteria inside a single honest-forest implementation: isotropic random-Fourier-feature maximum mean discrepancy (MMD), an anisotropic diagonal-bandwidth variant, an adaptive per-split frequency-selection variant, and a non-kernel sliced-Wasserstein criterion, together with post-hoc kernel-mean shrinkage of the forest weights. Using paired-seed comparisons across synthetic quantile mechanisms, real univariate benchmarks, a California-housing subsample curve, and multivariate synthetic and real responses, we characterize where each extension pays. Three findings recur. First, among distributional criteria ordinary isotropic MMD is already close to best in class: the anisotropic, adaptive-frequency, and sliced-Wasserstein extensions, and post-hoc shrinkage, do not systematically improve on it. Second, on scalar tabular regression mean-based CART splitting remains the robust default and wins many cells. Third, multivariate responses are the regime where distributional splitting clearly earns its keep, most sharply on a pure-dependence copula where the energy score separates the criteria even though marginal CRPS does not. The evidence supports a simple allocation story: distributional splitting helps only when non-location structure is both present and estimable; otherwise it dilutes split-selection power away from the mean. All criteria, the honest forest, and the paired-comparison harness are implemented in the open-source \texttt{drforest} library, whose Rust-backed split search makes broad criterion sweeps inexpensive.