Li-Xin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Li-Xin Zhang has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
Feifang Hu
Department of Statistics, George Washington University, Washington D.C., USA
11 shared publications- Siu Hung Cheung
Department of Statistics The Chinese University of Hong Kong Hong Kong China
11 shared publications - Wai-Sum Chan
Department of Finance, The Chinese University of Hong Kong, Hong Kong
8 shared publications - Ke-Ang Fu
Department of Statistics, Zhejiang University City College, Hangzhou, China
6 shared publications - Feifang Hu
Department of Statistics, University of Virginia, Charlottesville, VA, USA
4 shared publications - Kangqiang Li
School of Mathematical Sciences Zhejiang University 310027 Hangzhou Zhejiang China
4 shared publications
Latest Publications
- 9 August 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (18-19) , e70697
Statistical Inference for Covariate‐Adaptive Randomization Procedures With Missing Covariates
Covariate‐adaptive randomization (CAR) is increasingly used in clinical trials to balance baseline covariates, and its statistical properties have therefore attracted considerable attention in recent years. However, most existing studies overlook the issue of missing covariates, which is a common occurrence in practice. In this paper, we establish the theoretical properties of hypothesis testing for treatment and covariate effects when missing covariates are imputed using the single imputation method. The results indicate that the traditional test is conservative under certain conditions. However, this conservativeness can be corrected using an adjusted test, leading to higher statistical power. Furthermore, we extend our framework to the multiple imputation setting and compare its performance with single imputation through simulations. Our results provide a theoretical foundation for applying CAR procedures in the presence of missing covariates.
- 9 August 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (18-19) , e70697
Statistical Inference for Covariate‐Adaptive Randomization Procedures With Missing Covariates
Covariate‐adaptive randomization (CAR) is increasingly used in clinical trials to balance baseline covariates, and its statistical properties have therefore attracted considerable attention in recent years. However, most existing studies overlook the issue of missing covariates, which is a common occurrence in practice. In this paper, we establish the theoretical properties of hypothesis testing for treatment and covariate effects when missing covariates are imputed using the single imputation method. The results indicate that the traditional test is conservative under certain conditions. However, this conservativeness can be corrected using an adjusted test, leading to higher statistical power. Furthermore, we extend our framework to the multiple imputation setting and compare its performance with single imputation through simulations. Our results provide a theoretical foundation for applying CAR procedures in the presence of missing covariates.
- 24 January 2025
- Published by Springer Nature in Acta Mathematica Sinica, English Series
- Vol. 41 (3) , 827-846
Strassen’s Law of the Iterated Logarithm under Sub-linear Expectations
- 24 January 2025
- Published by Springer Nature in Acta Mathematica Sinica, English Series
- Vol. 41 (3) , 827-846
Strassen’s Law of the Iterated Logarithm under Sub-linear Expectations
- 21 October 2024
- Published by Springer Nature in Communications in Mathematics and Statistics
- Vol. 14 (4) , 1-21
General Central Limit Theorems for m-Dependent Random Variables Under Sub-linear Expectations
- 21 October 2024
- Published by Springer Nature in Communications in Mathematics and Statistics
- Vol. 14 (4) , 1-21
General Central Limit Theorems for m-Dependent Random Variables Under Sub-linear Expectations
- 16 September 2024
- Published by Wiley in Statistics in Medicine
- Vol. 43 (27) , 5047-5059
Group Response‐Adaptive Randomization With Delayed and Missing Responses
Response‐adaptive randomization (RAR) procedures have been extensively studied in the literature, but most of the procedures rely on updating the randomization after each response, which is impractical in many clinical trials. In this article, we propose a new family of RAR procedures that dynamically update based on the responses of a group of individuals, either when available or at fixed time intervals (weekly or biweekly). We show that the proposed design retains the essential theoretical properties of Hu and Zhang's doubly adaptive biased coin designs (DBCD), and performs well in scenarios involving delayed and randomly missing responses. Numerical studies have been conducted to demonstrate that the new proposed group doubly adaptive biased coin design has similar properties to the Hu and Zhang's DBCDs in different situations. We also apply the new design to a real clinical trial, highlighting its advantages and practicality. Our findings open the door to studying the properties of other group response adaptive designs, such as urn models, and facilitate the application of response‐adaptive randomized clinical trials in practice.
- 16 September 2024
- Published by Wiley in Statistics in Medicine
- Vol. 43 (27) , 5047-5059
Group Response‐Adaptive Randomization With Delayed and Missing Responses
Response‐adaptive randomization (RAR) procedures have been extensively studied in the literature, but most of the procedures rely on updating the randomization after each response, which is impractical in many clinical trials. In this article, we propose a new family of RAR procedures that dynamically update based on the responses of a group of individuals, either when available or at fixed time intervals (weekly or biweekly). We show that the proposed design retains the essential theoretical properties of Hu and Zhang's doubly adaptive biased coin designs (DBCD), and performs well in scenarios involving delayed and randomly missing responses. Numerical studies have been conducted to demonstrate that the new proposed group doubly adaptive biased coin design has similar properties to the Hu and Zhang's DBCDs in different situations. We also apply the new design to a real clinical trial, highlighting its advantages and practicality. Our findings open the door to studying the properties of other group response adaptive designs, such as urn models, and facilitate the application of response‐adaptive randomized clinical trials in practice.
- 24 August 2024
- Published by Springer Nature in Lifetime Data Analysis
- Vol. 30 (4) , 742-775
Copula-based analysis of dependent current status data with semiparametric linear transformation model
This paper discusses regression analysis of current status data with dependent censoring, a problem that often occurs in many areas such as cross-sectional studies, epidemiological investigations and tumorigenicity experiments. Copula model-based methods are commonly employed to tackle this issue. However, these methods often face challenges in terms of model and parameter identification. The primary aim of this paper is to propose a copula-based analysis for dependent current status data, where the association parameter is left unspecified. Our method is based on a general class of semiparametric linear transformation models and parametric copulas. We demonstrate that the proposed semiparametric model is identifiable under certain regularity conditions from the distribution of the observed data. For inference, we develop a sieve maximum likelihood estimation method, using Bernstein polynomials to approximate the nonparametric functions involved. The asymptotic consistency and normality of the proposed estimators are established. Finally, to demonstrate the effectiveness and practical applicability of our method, we conduct an extensive simulation study and apply the proposed method to a real data example.
- 24 August 2024
- Published by Springer Nature in Lifetime Data Analysis
- Vol. 30 (4) , 742-775
Copula-based analysis of dependent current status data with semiparametric linear transformation model
This paper discusses regression analysis of current status data with dependent censoring, a problem that often occurs in many areas such as cross-sectional studies, epidemiological investigations and tumorigenicity experiments. Copula model-based methods are commonly employed to tackle this issue. However, these methods often face challenges in terms of model and parameter identification. The primary aim of this paper is to propose a copula-based analysis for dependent current status data, where the association parameter is left unspecified. Our method is based on a general class of semiparametric linear transformation models and parametric copulas. We demonstrate that the proposed semiparametric model is identifiable under certain regularity conditions from the distribution of the observed data. For inference, we develop a sieve maximum likelihood estimation method, using Bernstein polynomials to approximate the nonparametric functions involved. The asymptotic consistency and normality of the proposed estimators are established. Finally, to demonstrate the effectiveness and practical applicability of our method, we conduct an extensive simulation study and apply the proposed method to a real data example.
- 11 June 2024
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 37 (4) , 1685-1713
Jackknife Model Averaging for Quantile Single-Index Coefficient Model
- 11 June 2024
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 37 (4) , 1685-1713
Jackknife Model Averaging for Quantile Single-Index Coefficient Model
- Open Access
Strong law of large numbers for $m$-dependent and stationary random variables under sub-linear expectations
The arm of this paper is to establish the strong law of large numbers (SLLN) of $m$-dependent random variables under the framework of sub-linear expectations. We establish the SLLN for a sequence of independent, but not necessarily identically distributed random variables. The study further extends the SLLN to $m$-dependent and stationary sequence of random variables with the condition $C_{\mathbb V}(|X_1|)<\infty$ which is the sufficient and necessary condition of SLLN in the case of independent and identically distributed random variables.Open AccessStrong law of large numbers for $m$-dependent and stationary random variables under sub-linear expectations
The arm of this paper is to establish the strong law of large numbers (SLLN) of $m$-dependent random variables under the framework of sub-linear expectations. We establish the SLLN for a sequence of independent, but not necessarily identically distributed random variables. The study further extends the SLLN to $m$-dependent and stationary sequence of random variables with the condition $C_{\mathbb V}(|X_1|)<\infty$ which is the sufficient and necessary condition of SLLN in the case of independent and identically distributed random variables. - 22 February 2024
- Published by Wiley in Statistics in Medicine
- Vol. 43 (9) , 1743-1758
Doubly adaptive biased coin design to improve Bayesian clinical trials with time‐to‐event endpoints
Clinical trialists often face the challenge of balancing scientific questions with other design features, such as improving efficiency, minimizing exposure to inferior treatments, and simultaneously comparing multiple treatments. While Bayesian response adaptive randomization (RAR) is a popular and effective method for achieving these objectives, it is known to have large variability and a lack of explicit theoretical results, making its use in clinical trials a subject of concern. It is desirable to propose a design that targets the same allocation proportion as Bayesian RAR and achieves the above objectives but addresses the concerns over Bayesian RAR. We propose the frequentist doubly adaptive biased coin designs (DBCD) targeting ethical allocation proportions from the Bayesian framework to satisfy different objectives in clinical trials with time‐to‐event endpoints. We derive the theoretical properties of the proposed adaptive randomization design and show through comprehensive numerical simulations that it can achieve ethical objectives without sacrificing efficiency. Our combined theoretical and numerical results offer a strong foundation for the practical use of RAR in real clinical trials.
- 22 February 2024
- Published by Wiley in Statistics in Medicine
- Vol. 43 (9) , 1743-1758
Doubly adaptive biased coin design to improve Bayesian clinical trials with time‐to‐event endpoints
Clinical trialists often face the challenge of balancing scientific questions with other design features, such as improving efficiency, minimizing exposure to inferior treatments, and simultaneously comparing multiple treatments. While Bayesian response adaptive randomization (RAR) is a popular and effective method for achieving these objectives, it is known to have large variability and a lack of explicit theoretical results, making its use in clinical trials a subject of concern. It is desirable to propose a design that targets the same allocation proportion as Bayesian RAR and achieves the above objectives but addresses the concerns over Bayesian RAR. We propose the frequentist doubly adaptive biased coin designs (DBCD) targeting ethical allocation proportions from the Bayesian framework to satisfy different objectives in clinical trials with time‐to‐event endpoints. We derive the theoretical properties of the proposed adaptive randomization design and show through comprehensive numerical simulations that it can achieve ethical objectives without sacrificing efficiency. Our combined theoretical and numerical results offer a strong foundation for the practical use of RAR in real clinical trials.
- Open Access
The limit points of the strong law of large numbers under the sub-linear expectations
Let $\{X_n;n\ge 1\}$ be a sequence of independent and identically distributed random variables in a regular sub-linear expectation space $(Ω,\mathscr{H},\widehat{\mathbb E})$ with the finite Choquet expectation, upper mean $\overlineμ $ and lower mean $\underlineμ $. Then for any Borel-measurable function $\varphi(x_1,\ldots,x_d)$ on $\mathbb R^d$ or continuous function $\varphi(x_1,x_2,\ldots)$ on $\mathbb R^{\mathbb N}$, $\sum_{i=1}^n X_i/n$ converges to $\underlineμ\wedge \varphi(X_1,X_2,\ldots)\wedge \overlineμ$ with upper capacity $1$. The limits of $\sum_{i=1}^nX_i/n$ can be with upper capacity 1 also a random set with boundaries being continuous functions or finite-dimensional Borel-measurable functions of $(X_1, X_2,\ldots)$.Open AccessThe limit points of the strong law of large numbers under the sub-linear expectations
Let $\{X_n;n\ge 1\}$ be a sequence of independent and identically distributed random variables in a regular sub-linear expectation space $(Ω,\mathscr{H},\widehat{\mathbb E})$ with the finite Choquet expectation, upper mean $\overlineμ $ and lower mean $\underlineμ $. Then for any Borel-measurable function $\varphi(x_1,\ldots,x_d)$ on $\mathbb R^d$ or continuous function $\varphi(x_1,x_2,\ldots)$ on $\mathbb R^{\mathbb N}$, $\sum_{i=1}^n X_i/n$ converges to $\underlineμ\wedge \varphi(X_1,X_2,\ldots)\wedge \overlineμ$ with upper capacity $1$. The limits of $\sum_{i=1}^nX_i/n$ can be with upper capacity 1 also a random set with boundaries being continuous functions or finite-dimensional Borel-measurable functions of $(X_1, X_2,\ldots)$.