arXiv subjects

Shenghao Qin

Publications and source records attributed to Shenghao Qin.

6 recordsLinked to original sources

arXiv2026

The Bag-and-Whisker Plot: A New Bagplot for Bivariate Data

The bagplot, also known as the "bag-and-bolster plot", is a notable extension of the boxplot from univariate to bivariate data. Although widely used, its practical application is hindered by two key limitations: the fixed inflation factor for outlier detection that does not adapt to the sample size, and the unstable convex hull used to visualize its fence. In this paper, we propose a new bagplot, namely the "bag-and-whisker plot", as an improvement method to address these limitations. Our framework recasts outlier detection as a multiple testing problem, yielding a data-adaptive fence that controls statistical error rates and enhances the reliability of outlier identification. To further resolve graphical instability, we introduce a refined visualization that abandons the convex hull (the bolster) with a direct rendering of the statistical fence, complemented by granular whiskers that effectively illustrate the data's spread. Extensive simulations and real-world data analyses demonstrate that our new bagplot exhibits superior adaptivity and robustness compared to the existing standard, and thus can be highly recommended for practical use. To increase the visibility of the work, a user-friendly R package named BagWhiskerPlot has been made publicly available on CRAN.

stat.ME↗

arXiv2025

Data-light Uncertainty Set Merging with Admissibility

This article introduces a Synthetics, Aggregation, and Test inversion (SAT) approach for merging diverse and potentially dependent uncertainty sets into a single unified set. The procedure is data-light, relying only on initial sets and their nominal levels, and it flexibly adapts to user-specified input sets with possibly varying coverage guarantees. SAT is motivated by the challenge of integrating uncertainty sets when only the initial sets and their control levels are available-for example, when merging confidence sets from distributed sites under communication constraints or combining conformal prediction sets generated by different algorithms or data splits. To address this, SAT constructs and aggregates novel synthetic test statistics, and then derive merged sets through test inversion. Our method leverages the duality between set estimation and hypothesis testing, ensuring reliable coverage in dependent scenarios. A key theoretical contribution is a rigorous analysis of SAT's properties, including its admissibility in the context of deterministic set merging. Both theoretical analyses and empirical results confirm the method's finite-sample coverage validity and desirable set sizes.

stat.ME↗

arXiv2025

A Unified Multiple Testing Framework based on rho-values

Multiple testing is an important research area with widespread scientific applications, including in biology and neuroscience. Among popularly adopted multiple testing procedures, many are based on p-values or Local false discovery rate (Lfdr) statistics. However, p-values--often obtained via the probability integral transform of standard test statistics--typically lack information from the alternatives, resulting in suboptimal performance. In contrast, Lfdr-based methods can achieve asymptotic optimality, but their ability to control the false discovery rate (FDR) hinges on accurate estimation of the Lfdr, which can be challenging, especially when incorporating side information. In this article, we introduce a novel and flexible class of statistics, termed rho-values, and develop a corresponding multiple testing framework that integrates the strengths of both p-values and Lfdr, while addressing their respective limitations. Specifically, the rho-value framework unifies these two paradigms through a two-step process: ranking and thresholding. The ranking induced by rho-values closely resembles that of Lfdr-based methods, while the thresholding step aligns with conventional p-value procedures. Therefore, the proposed framework guarantees FDR control under mild assumptions; it maintains the integrity of the structural information encoded by the summary statistics and the auxiliary covariates, and hence can be asymptotically optimal. We demonstrate the advantages of the rho-value framework through comprehensive simulations and analyses of two real datasets: one from microbiome research and another related to attention deficit hyperactivity disorder (ADHD).

stat.ME↗

arXiv2023

Alteration Detection of Tensor Dependence Structure via Sparsity-Exploited Reranking Algorithm

Tensor-valued data arise frequently from a wide variety of scientific applications, and many among them can be translated into an alteration detection problem of tensor dependence structures. In this article, we formulate the problem under the popularly adopted tensor-normal distributions and aim at two-sample correlation/partial correlation comparisons of tensor-valued observations. Through decorrelation and centralization, a separable covariance structure is employed to pool sample information from different tensor modes to enhance the power of the test. Additionally, we propose a novel Sparsity-Exploited Reranking Algorithm (SERA) to further improve the multiple testing efficiency. The algorithm is approached through reranking of the p-values derived from the primary test statistics, by incorporating a carefully constructed auxiliary tensor sequence. Besides the tensor framework, SERA is also generally applicable to a wide range of two-sample large-scale inference problems with sparsity structures, and is of independent interest. The asymptotic properties of the proposed test are derived and the algorithm is shown to control the false discovery at the pre-specified level. We demonstrate the efficacy of the proposed method through intensive simulations and two scientific applications.

stat.ME↗

arXiv2019

Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process

Predicting surrounding vehicle behaviors are critical to autonomous vehicles when negotiating in multi-vehicle interaction scenarios. Most existing approaches require tedious training process with large amounts of data and may fail to capture the propagating uncertainty in interaction behaviors. The multi-vehicle behaviors are assumed to be generated from a stochastic process. This paper proposes an attentive recurrent neural process (ARNP) approach to overcome the above limitations, which uses a neural process (NP) to learn a distribution of multi-vehicle interaction behavior. Our proposed model inherits the flexibility of neural networks while maintaining Bayesian probabilistic characteristics. Constructed by incorporating NPs with recurrent neural networks (RNNs), the ARNP model predicts the distribution of a target vehicle trajectory conditioned on the observed long-term sequential data of all surrounding vehicles. This approach is verified by learning and predicting lane-changing trajectories in complex traffic scenarios. Experimental results demonstrate that our proposed method outperforms previous counterparts in terms of accuracy and uncertainty expressiveness. Moreover, the meta-learning instinct of NPs enables our proposed ARNP model to capture global information of all observations, thereby being able to adapt to new targets efficiently.

cs.RO↗

arXiv2019

Recurrent Attentive Neural Process for Sequential Data

Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction accuracy of NPs by incorporating attention mechanism among contexts and targets. In a number of real-world applications such as robotics, finance, speech, and biology, it is critical to learn the temporal order and recurrent structure from sequential data. However, the capability of NPs capturing these properties is limited due to its permutation invariance instinct. In this paper, we proposed the Recurrent Attentive Neural Process (RANP), or alternatively, Attentive Neural Process-RecurrentNeural Network(ANP-RNN), in which the ANP is incorporated into a recurrent neural network. The proposed model encapsulates both the inductive biases of recurrent neural networks and also the strength of NPs for modelling uncertainty. We demonstrate that RANP can effectively model sequential data and outperforms NPs and LSTMs remarkably in a 1D regression toy example as well as autonomous-driving applications.

cs.LG↗