arXiv subjects

Shonosuke Sugasawa

Publications and source records attributed to Shonosuke Sugasawa.

At least 37 records · Page 2Linked to original sources

arXiv2026

Bayesian Estimation of Variance under Fine Stratification via Mean-Variance Smoothing

Fine stratification survey is useful in many applications as its point estimator is unbiased, but the variance estimator under the design cannot be easily obtained, particularly when the sample size per stratum is as small as one unit. One common practice to overcome this difficulty is to collapse strata in pairs to create pseudo-strata and then estimate the variance. The estimator of variance achieved is not design-unbiased, and the positive bias increases as the population means of the paired pseudo-strata become more variant. The resulting confidence intervals can be unnecessarily large. In this paper, we propose a new Bayesian estimator for variance which does not rely on collapsing strata, unlike the previous methods given in the literature. We employ the penalized spline method for smoothing the mean and variance together in a nonparametric way. Furthermore, we make comparisons with the earlier work of Breidt et al. (2016). Throughout multiple simulation studies and an illustration using data from the National Survey of Family Growth (NSFG), we demonstrate the favorable performance of our methodology.

stat.ME↗

arXiv2026

Difference-in-Differences under Local Dependence on Networks

Estimating causal effects under interference, where the stable unit treatment value assumption is violated, is critical in fields such as regional and public economics. Much of the existing research on causal inference under interference relies on a pre-specified "exposure mapping". This paper focuses on difference-in-difference and proposes a nonparametric identification strategy for direct and indirect average treatment effects under local interference on an observed network. In particular, we proposed a new concept of an indirect effect measuring the total outward influence of the intervension. Based on parallel trends assumption conditional on the neighborhood treatment vector, we develop inverse probability weighted and doubly robust estimators. We establish their asymptotic properties, including consistency under misspecification of nuisance models under some regularity conditions. Simulation studies and an empirical application demonstrate the effectiveness of the proposed method.

stat.ME↗

arXiv2026

Robust Global Fr'echet Regression via Weight Regularization

The Fréchet regression is a useful method for modeling random objects in a general metric space given Euclidean covariates. However, the conventional approach could be sensitive to outlying objects in the sense that the distance from the regression surface is large compared to the other objects. In this study, we develop a robust version of the global Fréchet regression by incorporating weight parameters into the objective function. We then introduce the Elastic net regularization, favoring a sparse vector of robust parameters to control the influence of outlying objects. We provide a computational algorithm to iteratively estimate the regression function and weight parameters, with providing a linear convergence property. We also propose the Bayesian information criterion to select the tuning parameters for regularization, which gives adaptive robustness along with observed data. The finite sample performance of the proposed method is demonstrated through numerical studies on matrix and distribution responses.

stat.CO↗

arXiv2026

Causal Inference under Threshold Manipulation: Bayesian Mixture Modeling and Heterogeneous Treatment Effects

Many marketing applications, including credit card incentive programs, offer rewards to customers who exceed specific spending thresholds to encourage increased consumption. Quantifying the causal effect of these thresholds on customers is crucial for effective marketing strategy design. Although regression discontinuity design is a standard method for such causal inference tasks, its assumptions can be violated when customers, aware of the thresholds, strategically manipulate their spending to qualify for the rewards. To address this issue, we propose a novel framework for estimating the causal effect under threshold manipulation. The main idea is to model the observed spending distribution as a mixture of two distributions: one representing customers strategically affected by the threshold, and the other representing those unaffected. To fit the mixture model, we adopt a two-step Bayesian approach consisting of modeling non-bunching customers and fitting a mixture model to a sample around the threshold. We show posterior contraction of the resulting posterior distribution of the causal effect under large samples. Furthermore, we extend this framework to a hierarchical Bayesian setting to estimate heterogeneous causal effects across customer subgroups, allowing for stable inference even with small subgroup sample sizes. We demonstrate the effectiveness of our proposed methods through simulation studies and illustrate their practical implications using a real-world marketing dataset.

stat.ME↗

arXiv2026

Bayesian Time-Varying Meta-Analysis via Hierarchical Mean-Variance Random-effects Models

Meta-analysis is widely used to integrate results from multiple experiments to obtain generalized insights. Since meta-analysis datasets are often heteroscedastic due to varying subgroups and temporal heterogeneity arising from experiments conducted at different time points, the typical meta-analysis approach, which assumes homoscedasticity, fails to adequately address this heteroscedasticity among experiments. This paper proposes a new Bayesian estimation method that simultaneously shrinks estimates of the means and variances of experiments using a hierarchical Bayesian approach while accounting for time effects through a Gaussian process. This method connects experiments via the hierarchical framework, enabling "borrowing strength" between experiments to achieve high-precision estimates of each experiment's mean. The method can flexibly capture potential time trends in datasets by modeling time effects with the Gaussian process. We demonstrate the effectiveness of the proposed method through simulation studies and illustrate its practical utility using a real marketing promotions dataset.

stat.ME↗

arXiv2026

Bayesian Doubly Robust Causal Inference via Posterior Coupling

Bayesian doubly robust (DR) causal inference faces a fundamental dilemma: joint modeling of outcome and propensity score suffers from the feedback problem where outcome information contaminates propensity score estimation, while two-step inference sacrifices valid posterior distributions for computational convenience. We resolve this dilemma through posterior coupling via entropic tilting. Our framework constructs independent posteriors for propensity score and outcome models, then couples them using entropic tilting to enforce the DR moment condition. This yields the first fully Bayesian DR estimator with an explicit posterior distribution. Theoretically, we establish three key properties: (i) when the outcome model is correctly specified, the tilted posterior coincides with the original; (ii) under propensity score model correctness, the posterior mean remains consistent despite outcome model misspecification; (iii) convergence rates improve for nonparametric outcome models. Simulations demonstrate superior bias reduction and efficiency compared to existing methods. We illustrate practical advantages of the proposed method through two applications: sensitivity analysis for unmeasured confounding in antihypertensive treatment effects on dementia, and high-dimensional confounder selection combining shrinkage priors with modified moment conditions for right heart catheterization mortality. We provide an R package implementing the proposed method.

stat.ME↗

arXiv2025

Sequential Adaptive Priors for Orthogonal Functions

We propose a novel class of prior distributions for sequences of orthogonal functions, which are frequently required in various statistical models such as functional principal component analysis (FPCA). Our approach constructs priors sequentially by imposing adaptive orthogonality constraints through a hierarchical formulation of conditionally normal distributions. The orthogonality is controlled via hyperparameters, allowing for flexible trade-offs between exactness and smoothness, which can be learned from the observed data. We illustrate the properties of the proposed prior and show that it leads to nearly orthogonal posterior estimates. The proposed prior is employed in Bayesian FPCA, providing more interpretable principal functions and efficient low-rank representations. Through simulation studies and analysis of human mobility data in Tokyo, we demonstrate the superior performance of our approach in inducing orthogonality and improving functional component estimation.

stat.ME↗

arXiv2025

Repulsive g-Priors for Regression Mixtures

Mixture regression models are powerful tools for capturing heterogeneous covariate-response relationships, yet classical finite mixtures and Bayesian nonparametric alternatives often suffer from instability or overestimation of clusters when component separability is weak. Recent repulsive priors improve parsimony in density mixtures by discouraging nearby components, but their direct extension to regression is nontrivial since separation must respect the predictive geometry induced by covariates. We propose a repulsive g-prior for regression mixtures that enforces separation in the Mahalanobis metric, penalizing components indistinguishable in the predictive mean space. This construction preserves conjugacy-like updates while introducing geometry-aware interactions, enabling efficient blocked-collapsed Gibbs sampling. Theoretically, we establish tractable normalizing bounds, posterior contraction rates, and shrinkage of tail mass on the number of components. Simulations under correlated and overlapping designs demonstrate improved clustering and prediction relative to independent, Euclidean-repulsive, and sparsity-inducing baselines.

stat.ME↗

arXiv2025

The Group R2D2 Shrinkage Prior for Sparse Linear Models with Grouped Covariates

Shrinkage priors are a popular Bayesian paradigm to handle sparsity in high-dimensional regression. Still limited, however, is a flexible class of shrinkage priors to handle grouped sparsity, where covariates exhibit some natural grouping structure. This paper proposes a novel extension of the $R^2$-induced Dirichlet Decomposition (R2D2) prior to accommodate grouped variable selection in linear regression models. The proposed method, called the Group R2D2 prior, employs a Dirichlet prior distribution on the coefficient of determination for each group, allowing for a flexible and adaptive shrinkage that operates at both group and individual variable levels. This approach improves the original R2D2 prior to handle grouped predictors, providing a balance between within-group dependence and group-level sparsity. We present several theoretical properties of this proposed prior distribution while also developing a Markov Chain Monte Carlo algorithm. Through simulation studies and real-data analysis, we demonstrate that our method outperforms traditional shrinkage priors in terms of both estimation accuracy, inference and prediction.

stat.ME↗

arXiv2025

Outlier-Robust Bayesian Multivariate Analysis with Correlation-Intact Sandwich Mixture

Handling outliers is a fundamental challenge in multivariate data analysis because outliers may distort the structures of correlation or conditional independence. Although robust Bayesian inference has been extensively studied in univariate settings, theoretical results ensuring posterior robustness in multivariate models are scarce. We propose a novel scale mixture of multivariate normals called correlation-intact sandwich mixtures, in which the scale parameters are real values and follow an unfolded log-Pareto distribution. Our theoretical results on posterior robustness in multivariate settings emphasize that the use of a symmetric, super heavy-tailed distribution for scale parameters is essential for achieving posterior robustness against element-wise contamination. The posterior inference for the proposed model is feasible using the developed efficient Gibbs sampling algorithm. The superiority of the proposed method was further illustrated further in simulation and empirical studies using graphical models and multivariate regression in the presence of complex outlier structures.

stat.ME↗

arXiv2025

On Misspecified Error Distributions in Bayesian Functional Clustering: Consequences and Remedies

Nonparametric Bayesian approaches provide a flexible framework for clustering without pre-specifying the number of groups, yet they are well known to overestimate the number of clusters, especially for functional data. We show that a fundamental cause of this phenomenon lies in misspecification of the error structure: errors are conventionally assumed to be independent across observed points in Bayesian functional models. Through high-dimensional clustering theory, we demonstrate that ignoring the underlying correlation leads to excess clusters regardless of the flexibility of prior distributions. Guided by this theory, we propose incorporating the underlying correlation structures via Gaussian processes and also present its scalable approximation with principled hyperparameter selection. Numerical experiments illustrate that even simple clustering based on Dirichlet processes performs well once error dependence is properly modeled.

stat.ME↗

arXiv2025

Ensemble Prediction via Covariate-dependent Stacking

This study proposes a novel approach to ensemble prediction, called "covariate-dependent stacking" (CDST). Unlike traditional stacking and model averaging methods, CDST allows model weights to vary flexibly as a function of covariates, thereby enhancing predictive performance in complex scenarios. We formulate the covariate-dependent weights through combinations of basis functions and estimate them via cross-validation optimization. To analyze the theoretical properties, we establish an oracle inequality regarding the expected loss to be minimized for estimating model weights. Through comprehensive simulation studies and an application to large-scale land price prediction, we demonstrate that the CDST consistently outperforms conventional model averaging methods, particularly on datasets where base models fail to capture the underlying complexity. Our findings suggest that the CDST is especially valuable for, but not limited to, spatio-temporal prediction problems, offering a powerful tool for researchers and practitioners across a wide spectrum of data analysis fields.

stat.ME↗

arXiv2025

Bayesian Benchmarking Small Area Estimation via Entropic Tilting

Benchmarking estimation and its risk evaluation is a practically important issue in small area estimation. While Bayesian methods have been widely adopted in small area estimation, existing benchmarking approaches are often ad-hoc, such as projecting each MCMC draw to satisfy the constraint. In contrast, our work provides a unified Bayesian formulation based on entropic tilting, which offers a more principled way to define the benchmarked posterior distribution. This approach yields benchmarked point estimates together with coherent uncertainty quantification. We first introduce general Monte Carlo methods for obtaining a benchmarked posterior under hierarchical Bayesian approaches and then show that the benchmarked posterior under empirical Bayesian frameworks can be obtained in an analytical form for some small area models. We demonstrate the usefulness of the proposed method through simulation and empirical studies.

stat.ME↗

arXiv2025

Noise-Robust Phase Connectivity Estimation via Bayesian Circular Functional Models

The phase locking value (PLV) is a widely used measure to detect phase connectivity. Main drawbacks of the standard PLV are it can be sensitive to noisy observations and does not provide uncertainty measures under finite samples. To overcome the difficulty, we propose a model-based PLV through nonparametric statistical modeling. Specifically, since the discrete time series of phase can be regarded as a functional observation taking values on circle, we employ a Bayesian model for circular-variate functional data, which gives denoising and inference on the resulting PLV values. The proposed model is defined through "wrapping" functional Gaussian models on real line, for which we develop an efficient posterior computation algorithm using Gibbs sampler. The usefulness of the proposed method is demonstrated through simulation experiments based on real EEG data.

stat.ME↗

arXiv2025

Robust Spatio-Temporal Distributional Regression

Motivated by investigating spatio-temporal patterns of the distribution of continuous variables, we consider describing the conditional distribution function of the response variable incorporating spatio-temporal components given predictors. In many applications, continuous variables are observed only as threshold-categorized data due to measurement constraints. For instance, ecological measurements often categorize sizes into intervals rather than recording exact values due to practical limitations. To recover the conditional distribution function of the underlying continuous variables, we consider a distribution regression employing models for binomial data obtained at each threshold value. However, depending on spatio-temporal conditions and predictors, the distribution function may frequently exhibit boundary values (zero or one), which can occur either structurally or randomly. This makes standard binomial models inadequate, requiring more flexible modeling approaches. To address this issue, we propose a boundary-inflated binomial model incorporating spatio-temporal components. The model is a three-component mixture of the binomial model and two Dirac measures at zero and one. We develop a computationally efficient Bayesian inference algorithm using Pólya-Gamma data augmentation and dynamic Gaussian predictive processes. Extensive simulation experiments demonstrate that our procedure significantly outperforms distribution regression methods based on standard binomial models across various scenarios.

stat.ME↗

arXiv2025

General Bayesian quantile regression for counts via generative modeling

Count data frequently arises in biomedical applications, such as the length of hospital stay. However, their discrete nature poses significant challenges for appropriately modeling conditional quantiles, which are crucial for understanding heterogeneous effects and variability in outcomes. To solve the practical difficulty, we propose a novel general Bayesian framework for quantile regression tailored to count data. We seek the regression parameter on the conditional quantile by minimizing the expected loss with respect to the distribution of the conditional quantile of the latent continuous variable associated with the observed count response variable. By modeling the unknown conditional distribution through a Bayesian nonparametric kernel mixture for the joint distribution of the count response and covariates, we obtain the posterior distribution of the regression parameter via a simple optimization. We numerically demonstrate that the proposed method improves bias and estimation accuracy of the existing crude approaches to count quantile regression. Furthermore, we analyze the length of hospital stay for acute myocardial infarction and demonstrate that the proposed method gives more interpretable and flexible results than the existing ones.

stat.ME↗

arXiv2025

Similarity-based Random Partition Distribution for Clustering Functional Data

Random partition distribution is a crucial tool for model-based clustering. This study advances the field of random partition in the context of functional spatial data, focusing on the challenges posed by hourly population data across various regions and dates. We propose an extension of the generalized Dirichlet process, named the similarity-based generalized Dirichlet process (SGDP)-type distribution, to address the limitations of simple random partition distributions (e.g., those induced by the Dirichlet process), such as an overabundance of clusters. This model prevents excess cluster production and incorporates pairwise similarity information to ensure accurate and meaningful clustering. The theoretical properties of the SGDP-type distribution are studied. Then, SGDP-type random partition is applied to a real-world dataset of hourly population flow in $500\text{m}$ meshes in the central part of Tokyo. In this empirical context, our method excels at detecting meaningful patterns in the data while accounting for spatial nuances. The results underscore the adaptability and utility of the method, showcasing its prowess in revealing intricate spatiotemporal dynamics. The proposed random partition will significantly contribute to urban planning, transportation, and policy-making and will be a helpful tool for understanding population dynamics and their implications.

stat.ME↗

arXiv2025

Prior Sensitivity Analysis without Model Re-fit

Prior sensitivity analysis is a fundamental method to check the effects of prior distributions on the posterior distribution in Bayesian inference. Exploring the posteriors under several alternative priors can be computationally intensive, particularly for complex latent variable models. To address this issue, we propose a novel method for quantifying the prior sensitivity that does not require model re-fit. Specifically, we present a method to compute the Hellinger and Kullback-Leibler distances between two posterior distributions with base and alternative priors, using Monte Carlo integration based only on the base posterior distribution, through novel integral expressions of the two distances. We also extend the above approach for assessing the influence of hyperpriors in general latent variable models. We demonstrate the proposed method through examples of a simple normal distribution model, hierarchical binomial-beta model, and Gaussian process regression model.

stat.ME↗