Publications

A rolling downside-threshold framework for defining persistent stablecoin depegging events and evaluating rare-event monitoring. Accepted for publication in Digital Finance; Jiajing Sun is the corresponding author.

This review examines when machine learning improves economic prediction, measurement, causal inference, policy learning, structural analysis, finance, and operational decision-making.

This article studies nonlinear and time-varying connectedness between supply-chain bottlenecks and green finance markets, including clean energy equities, green bonds, and carbon prices.

This paper uses Eora MRIO data for 189 countries (2010-2021) to map green, blue, and grey embodied-water flows and examine how virtual-water positions relate to industrial structure, trade openness, water withdrawal capacity, and growth outcomes.

This article examines risk connectedness and resilience across green finance, green cryptocurrency, and non-green cryptocurrency markets using a time-frequency higher-order moment framework.

This article studies Argentina as a fragmented USD access system and uses quantile time-frequency connectedness analysis to examine risk transmission among official, parallel, and stablecoin-based dollar channels.

This article develops a mathematical-sciences framework for trustworthy AI corpora, organizing corpus trustworthiness around representativeness, consistency, fairness, privacy, and robustness across the lifecycle of collection, cleaning, augmentation, and auditing.

Jiajing Sun, Zhuo Lin and Brendan McCabe develop a cross-validation method for combining integer-valued autoregressive models. The paper has been accepted by the China Journal of Econometrics.

This paper develops an adjusted-range-based self-normalized method for autocorrelation tests in time series analysis. The approach enhances statistical power while maintaining robustness against model misspecification.

We propose an adjusted-range-based self-normalization method for testing structural stability in functional data. This approach improves computational efficiency and performs well in empirical applications to temperature data from New York Central Park Weather Station.

This paper introduces a novel method for structural break testing using the Kolmogorov-Smirnov type test, enhanced by an adjusted-range-based self-normalization approach.

This paper investigates the relationship between governmental capabilities and CO₂ emissions in the context of global decarbonization efforts.

This paper analyzes social media interactions between the Chinese government and the public using WeChat official accounts during the COVID-19 pandemic.

This paper examines the relationship between innovation, carbon emissions, and the pollution haven hypothesis in the context of climate capitalism.

This paper develops a score statistic for testing the presence of a stochastic trend in the context of conditional variances in time series data.

This paper proposes a self-normalized method for constructing confidence intervals for censored dependent data, improving the robustness and accuracy of inference.

本论文提出了一种基于调整样本值域的自正则方法，用于检验时间序列中的结构性变化。该方法在强依赖性和重尾分布下表现良好，能够提升结构性变化检验的准确性。

本论文提出了一种基于Katz分布的计数数据自回归模型，并将其应用于预测呼吸系统疾病的发病人数。该方法在处理高维数据时表现出了较好的预测能力。

This paper investigates Chinese leadership practices, focusing on provincial perspectives on promotion and performance.

This paper introduces an RKHS-based approach for double-penalized regression in high-dimensional partially linear models.

This paper proposes an information diffusion-based model for predicting oil futures prices, addressing the dynamics of information spread in financial markets.

This paper develops score statistics for testing serial dependence in count data, particularly in time series analysis.

This paper presents a method for variable selection in regression settings involving treatment selection.

This paper develops a bootstrap test for comparing two variances, focusing on its simulation of size and power in small samples.