Hansheng Wang
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
Hansheng Wang has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
Chih-Ling Tsai
University of California, Davis - Graduate School of Management
11 shared publications- Xuening Zhu
Fudan University
8 shared publications Rui Pan
School of Statistics and Mathematics, Central University of Finance and Economics, Beijing, China
7 shared publicationsWei Lan
Peking University - Guanghua School of Management
7 shared publications- Runze Li
Department of Statistics, Pennsylvania State University
6 shared publications - Rui Pan
School of Statistics and Mathematics, Central University of Finance and Economics
4 shared publications
Latest Publications
- Open Access
- 28 July 2026
- Published by Elsevier in SSRN Electronic Journal
Cubic-Rate Estimators with Distributed Variable Selection in Massive Data
Estimators with cube root convergence rate are widely encountered across various fields, yet effective variable selection for such estimators with massive distributed data remains an open question. To fulfill this theoretical gap, two novel methods are proposed. The first method directly applies a penalty term to the original loss function under a divide-and-conquer framework. The aggregated shrinkage estimator demonstrates faster convergence rate than cube root and is asymptotically normal. The second method introduces a penalized surrogate loss and a multi-round distributed estimation process. The resulting estimator is square-root consistent up to a multiplicative scalar and is asymptotically normal. With appropriate penalization, both methods achieve variable selection consistency and the oracle property (Fan and Li, 2001). Both proposed methods are directly applicable to a wide class of cubic-rate estimators, including maximum score estimator, least median of squares estimator and value search estimator as special cases. Extensive simulation studies demonstrate finite sample performance and an airline on-time dataset is analyzed for illustration.
- 28 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCubic-Rate Estimators with Distributed Variable Selection in Massive Data
Estimators with cube root convergence rate are widely encountered across various fields, yet effective variable selection for such estimators with massive distributed data remains an open question. To fulfill this theoretical gap, two novel methods are proposed. The first method directly applies a penalty term to the original loss function under a divide-and-conquer framework. The aggregated shrinkage estimator demonstrates faster convergence rate than cube root and is asymptotically normal. The second method introduces a penalized surrogate loss and a multi-round distributed estimation process. The resulting estimator is square-root consistent up to a multiplicative scalar and is asymptotically normal. With appropriate penalization, both methods achieve variable selection consistency and the oracle property (Fan and Li, 2001). Both proposed methods are directly applicable to a wide class of cubic-rate estimators, including maximum score estimator, least median of squares estimator and value search estimator as special cases. Extensive simulation studies demonstrate finite sample performance and an airline on-time dataset is analyzed for illustration.
- 2 June 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Selecting and Testing Asset-Pricing Models: A Stepwise Approach
The asset-pricing literature emphasizes factor models that minimize pricing errors but overlooks unselected candidate factors that could enhance the performance of test assets. This paper proposes a framework for factor model selection and testing by (i) selecting the optimal model that spans the joint efficient frontier of test assets and all candidate factors and (ii) testing pricing performance on both test assets and unselected candidate factors. Our framework updates a baseline model (e.g., capital asset-pricing model) sequentially by adding or removing factors based on asset-pricing tests. Ensuring model selection consistency, our framework utilizes the asset-pricing duality; minimizing cross-sectionally unexplained pricing errors aligns with maximizing the Sharpe ratio of the selected factor model. Empirical evidence shows that workhorse factor models fail asset-pricing tests, whereas our proposed eight-factor model is not rejected and exhibits robust out-of-sample performance. This paper was accepted by Lukas Schmid, finance. Funding: G. Feng acknowledges financial support from the Hong Kong Research Grants Council [Grant GRF11502023] and the National Natural Science Foundation of China [Grant 72203190]. G. Feng is partially supported by the InnoHK Initiative of the Innovation and Technology Commission of the Hong Kong SAR and the Laboratory for AI-Powered Financial Technologies. The research of W. Lan was supported by the National Key R&D Program of China [Grant 2022YFA1003702]; the National Natural Science Foundation of China [Grants 72422020, 72333001, and 12531011]; and the Joint Lab of Data Science and Business Intelligence at Southwestern University of Finance and Economics. The research of H. Wang was partially supported by the National Natural Science Foundation of China [Grants 72495123 and 12271012]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.07804 .
- 2 June 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Selecting and Testing Asset-Pricing Models: A Stepwise Approach
The asset-pricing literature emphasizes factor models that minimize pricing errors but overlooks unselected candidate factors that could enhance the performance of test assets. This paper proposes a framework for factor model selection and testing by (i) selecting the optimal model that spans the joint efficient frontier of test assets and all candidate factors and (ii) testing pricing performance on both test assets and unselected candidate factors. Our framework updates a baseline model (e.g., capital asset-pricing model) sequentially by adding or removing factors based on asset-pricing tests. Ensuring model selection consistency, our framework utilizes the asset-pricing duality; minimizing cross-sectionally unexplained pricing errors aligns with maximizing the Sharpe ratio of the selected factor model. Empirical evidence shows that workhorse factor models fail asset-pricing tests, whereas our proposed eight-factor model is not rejected and exhibits robust out-of-sample performance. This paper was accepted by Lukas Schmid, finance. Funding: G. Feng acknowledges financial support from the Hong Kong Research Grants Council [Grant GRF11502023] and the National Natural Science Foundation of China [Grant 72203190]. G. Feng is partially supported by the InnoHK Initiative of the Innovation and Technology Commission of the Hong Kong SAR and the Laboratory for AI-Powered Financial Technologies. The research of W. Lan was supported by the National Key R&D Program of China [Grant 2022YFA1003702]; the National Natural Science Foundation of China [Grants 72422020, 72333001, and 12531011]; and the Joint Lab of Data Science and Business Intelligence at Southwestern University of Finance and Economics. The research of H. Wang was partially supported by the National Natural Science Foundation of China [Grants 72495123 and 12271012]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.07804 .
- Open Access
Selecting and Testing Asset Pricing Models: A Stepwise Approach
The asset pricing literature emphasizes factor models that minimize pricing errors but overlooks unselected candidate factors that could enhance the performance of test assets. This paper proposes a framework for factor model selection and testing by (i) selecting the optimal model that spans the joint efficient frontier of test assets and all candidate factors, and (ii) testing pricing performance on both test assets and unselected candidate factors. Our framework updates a baseline model (e.g., CAPM) sequentially by adding or removing factors based on asset pricing tests. Ensuring model selection consistency, our framework utilizes the asset pricing duality: minimizing cross-sectionally unexplained pricing errors aligns with maximizing the Sharpe ratio of the selected factor model. Empirical evidence shows that workhorse factor models fail asset pricing tests, whereas our proposed 8-factor model is not rejected and exhibits robust out-of-sample performance.
Open AccessSelecting and Testing Asset Pricing Models: A Stepwise Approach
The asset pricing literature emphasizes factor models that minimize pricing errors but overlooks unselected candidate factors that could enhance the performance of test assets. This paper proposes a framework for factor model selection and testing by (i) selecting the optimal model that spans the joint efficient frontier of test assets and all candidate factors, and (ii) testing pricing performance on both test assets and unselected candidate factors. Our framework updates a baseline model (e.g., CAPM) sequentially by adding or removing factors based on asset pricing tests. Ensuring model selection consistency, our framework utilizes the asset pricing duality: minimizing cross-sectionally unexplained pricing errors aligns with maximizing the Sharpe ratio of the selected factor model. Empirical evidence shows that workhorse factor models fail asset pricing tests, whereas our proposed 8-factor model is not rejected and exhibits robust out-of-sample performance.
- 15 June 2025
- Published by Springer Nature
- p. 41-52
High Resolution Image Classification with Rich Text Information Based on Graph Convolution Neural Network
- 15 June 2025
- Published by Springer Nature
- p. 41-52
High Resolution Image Classification with Rich Text Information Based on Graph Convolution Neural Network
- 1 January 2025
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 34 (4) , 2277-2300
Distributed Logistic Regression for Massive Data with Rare Events
- 1 January 2025
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 34 (4) , 2277-2300
Distributed Logistic Regression for Massive Data with Rare Events
- 24 October 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 139
A geometric model with stochastic error for abnormal motion detection of portal crane bucket grab
- 24 October 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 139
A geometric model with stochastic error for abnormal motion detection of portal crane bucket grab
- 1 January 2024
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 17 (4) , 605-622
Estimating extreme value index by subsampling for massive datasets with heavy-tailed distributions
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2024
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 17 (4) , 605-622
Estimating extreme value index by subsampling for massive datasets with heavy-tailed distributions
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- Open Access
Mixture Conditional Regression with Ultrahigh Dimensional Text Data for Estimating Extralegal Factor Effects
Testing judicial impartiality is a problem of fundamental importance in empirical legal studies, for which standard regression methods have been popularly used to estimate the extralegal factor effects. However, those methods cannot handle control variables with ultrahigh dimensionality, such as found in judgment documents recorded in text format. To solve this problem, we develop a novel mixture conditional regression (MCR) approach, assuming that the whole sample can be classified into a number of latent classes. Within each latent class, a standard linear regression model can be used to model the relationship between the response and a key feature vector, which is assumed to be of a fixed dimension. Meanwhile, ultrahigh dimensional control variables are then used to determine the latent class membership, where a Naïve Bayes type model is used to describe the relationship. Hence, the dimension of control variables is allowed to be arbitrarily high. A novel expectation-maximization algorithm is developed for model estimation. Therefore, we are able to estimate the interested key parameters as efficiently as if the true class membership were known in advance. Simulation studies are presented to demonstrate the proposed MCR method. A real dataset of Chinese burglary offenses is analyzed for illustration purpose.
Open AccessMixture Conditional Regression with Ultrahigh Dimensional Text Data for Estimating Extralegal Factor Effects
Testing judicial impartiality is a problem of fundamental importance in empirical legal studies, for which standard regression methods have been popularly used to estimate the extralegal factor effects. However, those methods cannot handle control variables with ultrahigh dimensionality, such as found in judgment documents recorded in text format. To solve this problem, we develop a novel mixture conditional regression (MCR) approach, assuming that the whole sample can be classified into a number of latent classes. Within each latent class, a standard linear regression model can be used to model the relationship between the response and a key feature vector, which is assumed to be of a fixed dimension. Meanwhile, ultrahigh dimensional control variables are then used to determine the latent class membership, where a Naïve Bayes type model is used to describe the relationship. Hence, the dimension of control variables is allowed to be arbitrarily high. A novel expectation-maximization algorithm is developed for model estimation. Therefore, we are able to estimate the interested key parameters as efficiently as if the true class membership were known in advance. Simulation studies are presented to demonstrate the proposed MCR method. A real dataset of Chinese burglary offenses is analyzed for illustration purpose.
- Open Access
Optimal Subsampling Bootstrap for Massive Data
The bootstrap is a widely used procedure for statistical inference because of its simplicity and attractive statistical properties. However, the vanilla version of bootstrap is no longer feasible computationally for many modern massive datasets due to the need to repeatedly resample the entire data. Therefore, several improvements to the bootstrap method have been made in recent years, which assess the quality of estimators by subsampling the full dataset before resampling the subsamples. Naturally, the performance of these modern subsampling methods is influenced by tuning parameters such as the size of subsamples, the number of subsamples, and the number of resamples per subsample. In this paper, we develop a novel hyperparameter selection methodology for selecting these tuning parameters. Formulated as an optimization problem to find the optimal value of some measure of accuracy of an estimator subject to computational cost, our framework provides closed-form solutions for the optimal hyperparameter values for subsampled bootstrap, subsampled double bootstrap and bag of little bootstraps, at no or little extra time cost. Using the mean square errors as a proxy of the accuracy measure, we apply our methodology to study, compare and improve the performance of these modern versions of bootstrap developed for massive data through simulation study. The results are promising.
Open AccessOptimal Subsampling Bootstrap for Massive Data
The bootstrap is a widely used procedure for statistical inference because of its simplicity and attractive statistical properties. However, the vanilla version of bootstrap is no longer feasible computationally for many modern massive datasets due to the need to repeatedly resample the entire data. Therefore, several improvements to the bootstrap method have been made in recent years, which assess the quality of estimators by subsampling the full dataset before resampling the subsamples. Naturally, the performance of these modern subsampling methods is influenced by tuning parameters such as the size of subsamples, the number of subsamples, and the number of resamples per subsample. In this paper, we develop a novel hyperparameter selection methodology for selecting these tuning parameters. Formulated as an optimization problem to find the optimal value of some measure of accuracy of an estimator subject to computational cost, our framework provides closed-form solutions for the optimal hyperparameter values for subsampled bootstrap, subsampled double bootstrap and bag of little bootstraps, at no or little extra time cost. Using the mean square errors as a proxy of the accuracy measure, we apply our methodology to study, compare and improve the performance of these modern versions of bootstrap developed for massive data through simulation study. The results are promising.
- 31 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9502-9513
A Sequential Addressing Subsampling Method for Massive Data Analysis Under Memory Constraint
The emergence of massive data in recent years brings challenges to automatic statistical inference. This is particularly true if the data are too numerous to be read into memory as a whole. Accordingly, new sampling techniques are needed to sample data from a hard drive. In this paper, we propose a sequential addressing subsampling (SAS) method that can sample data directly from the hard drive. The newly proposed SAS method is time saving in terms of addressing cost compared to that of the random addressing subsampling (RAS) method. Estimators (e.g., the sample mean) based on the SAS subsamples are constructed, and their properties are studied. We conduct a series of simulation studies to verify the finite sample performance of the proposed SAS estimators. The time cost is also compared between the SAS and RAS methods. An analysis of the airline data is presented for illustration purpose.
- 31 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9502-9513
A Sequential Addressing Subsampling Method for Massive Data Analysis Under Memory Constraint
The emergence of massive data in recent years brings challenges to automatic statistical inference. This is particularly true if the data are too numerous to be read into memory as a whole. Accordingly, new sampling techniques are needed to sample data from a hard drive. In this paper, we propose a sequential addressing subsampling (SAS) method that can sample data directly from the hard drive. The newly proposed SAS method is time saving in terms of addressing cost compared to that of the random addressing subsampling (RAS) method. Estimators (e.g., the sample mean) based on the SAS subsamples are constructed, and their properties are studied. We conduct a series of simulation studies to verify the finite sample performance of the proposed SAS estimators. The time cost is also compared between the SAS and RAS methods. An analysis of the airline data is presented for illustration purpose.