arXiv subjects

Jiangyan Zhao

Publications and source records attributed to Jiangyan Zhao.

3 recordsLinked to original sources

arXiv2026

Shared Keyboard: An improved Bayesian design for phase I clinical trials via Beta kernel process

Model-assisted interval designs such as the Keyboard design are transparent and easy to implement in phase I oncology trials. However, interim decisions based solely on data from the current dose may overlook informative signals from neighbouring doses, leading to unnecessary escalation or de-escalation. We propose the shared Keyboard design, a Bayesian model-assisted design that replaces the independent beta--binomial updating scheme at each dose with a posterior induced by a Beta kernel process using kernel-weighted pseudo-counts. The design preserves the decision structure of the Keyboard design while enabling controlled borrowing across nearby doses. To prioritise overdose control, we propose an asymmetric kernel that assigns greater weight to toxicities observed at higher doses during escalation. We further extend the proposed design to accommodate adaptive dose insertion when the initial dose grid is inadequate and time-to-event outcomes when late-onset toxicities are present. Extensive simulation studies demonstrate substantial improvements in both accuracy and safety for identifying the maximum tolerated dose. In settings involving dose insertion, the proposed design identifies inserted target doses more effectively than adaptive dose modification while maintaining a comparable modification rate.

stat.AP↗

arXiv2026

A Unified Framework for Density Estimation under Right-Censored Point-Centred Quarter Sampling

While the point-centred quarter method (PCQM) is widely used for density estimation, existing methods for handling right-censored data from truncated search radii rely primarily on a Poisson model assuming complete spatial randomness (CSR), leaving a critical gap for spatially aggregated populations. To address this limitation, we develop a unified likelihood- and moment-based framework for right-censored point-centred quarter sampling under both Poisson and negative binomial distribution (NBD) models. In particular, the proposed NBD-based estimators explicitly account for spatial aggregation and censoring simultaneously, extending distance-based inference beyond the CSR setting. Extensive simulations and applications to fully mapped forest plots reveal that the NBD-based MLE delivers the most robust overall performance across diverse ecological scenarios. Across more than 100 species from fully mapped forest plots, the proposed NBD-based MLE approximately reduced absolute relative bias by a median of 0.10 compared with existing censored estimators, representing a relative improvement of over 30%. Ultimately, our framework provides a rigorously validated and practically useful toolkit for analysing censored point-to-tree distance data.

stat.ME↗

arXiv2025

BKP: An R Package for Beta Kernel Process Modeling

Estimating input-dependent probability surfaces from binary, binomial, categorical, or multinomial response data is a common task in statistics and machine learning. Latent Gaussian process classifiers provide flexible nonparametric models for such problems, but posterior inference with discrete responses typically requires approximation or simulation. We discuss an implementation of probability-scale beta and Dirichlet kernel models in the \pkg{BKP} package for \proglang{R}. The package implements the Beta Kernel Process (BKP), which uses kernel-weighted pseudo-count aggregation and beta-binomial conjugacy to obtain closed-form conjugate posterior summaries and posterior predictive distributions for binomial probabilities. It also implements the Dirichlet Kernel Process (DKP) for multi-class responses, together with TwinBKP and TwinDKP, scalable twinning-based global-local approximations for larger datasets. The resulting workflow supports transparent kernel-weighted evidence borrowing, several kernel families, fixed and data-adaptive priors, effective-sample-size calibration, loss-based hyperparameter tuning, and standard S3 methods for fitting, prediction, simulation, visualization, and extraction of posterior summaries. Reproducible examples demonstrate probability-surface estimation, binary and multi-class classification, computational comparison, and real-data applications to \emph{Loa loa} infection prevalence mapping and Mourning Warbler distribution modeling.

stat.CO↗