Changcheng Li
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
Changcheng Li has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Runze Li
Department of Statistics, Pennsylvania State University
4 shared publications Songshan Yang
The Center for Applied Statistics and Institute of Statistics and Big Data, Renmin University of China, Beijing, China
2 shared publications- Alex Zhao
Department of Statistics, Pennsylvania State University at University Park
1 shared publication Cai-Yan Cui
Huazhong University of Science and Technology
1 shared publication- Guo-Liang Tian
Department of Statistics and Data Science, Southern University of Science and Technology, Shenzhen, P. R. China
1 shared publication Jiawei Wen
Meta, Menlo Park, CA
1 shared publication
Latest Publications
- 23 May 2025
- Published by Springer Nature in Science China Mathematics
- Vol. 68 (8) , 1841-1868
Model-free variable selection in high dimension via constrained kernel regression
- 23 May 2025
- Published by Springer Nature in Science China Mathematics
- Vol. 68 (8) , 1841-1868
Model-free variable selection in high dimension via constrained kernel regression
- 1 October 2024
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 52 (5) , 2034-2058
Testing high-dimensional regression coefficients in linear models
This paper is concerned with statistical inference for regression coefficients in high-dimensional linear regression models. We propose a new method for testing the coefficient vector of the high-dimensional linear models, and establish the asymptotic normality of our proposed test statistic with the aid of the martingale central limit theorem. We derive the asymptotical relative efficiency (ARE) of the proposed test with respect to the test proposed in Zhong and Chen (J. Amer. Statist. Assoc. 106 (2011) 260–274), and show that the ARE is always greater or equal to one under the local alternative studied in this paper. Our numerical studies imply that the proposed test with critical values derived from its asymptotical normal distribution may retain Type I error rate very well. Our numerical comparison demonstrates the proposed test performs better than existing ones in terms of powers. We further illustrate our proposed method with a real data example.
- 1 October 2024
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 52 (5) , 2034-2058
Testing high-dimensional regression coefficients in linear models
This paper is concerned with statistical inference for regression coefficients in high-dimensional linear regression models. We propose a new method for testing the coefficient vector of the high-dimensional linear models, and establish the asymptotic normality of our proposed test statistic with the aid of the martingale central limit theorem. We derive the asymptotical relative efficiency (ARE) of the proposed test with respect to the test proposed in Zhong and Chen (J. Amer. Statist. Assoc. 106 (2011) 260–274), and show that the ARE is always greater or equal to one under the local alternative studied in this paper. Our numerical studies imply that the proposed test with critical values derived from its asymptotical normal distribution may retain Type I error rate very well. Our numerical comparison demonstrates the proposed test performs better than existing ones in terms of powers. We further illustrate our proposed method with a real data example.
- 1 January 2023
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 32, 2007-2022
Spectral Properties of Rescaled Sample Correlation Matrix
- 1 January 2023
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 32, 2007-2022
Spectral Properties of Rescaled Sample Correlation Matrix
- 1 December 2022
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 32 (3) , 1074-1082
Regularized Linear Programming Discriminant Rule with Folded Concave Penalty for Ultrahigh-Dimensional Data
We propose the regularized linear programming discriminant (LPD) rule with folded concave penalty in the ultrahigh-dimensional regime. We use the local linear approximation (LLA) algorithm to redirect the model with folded concave penalty to a weighted model. The strong oracle property of the solution constructed by the one-step local linear approximation (LLA) algorithm is verified. In addition, we propose efficient and parallelizable algorithms based on feature space split to address the computational challenges due to ultrahigh dimensionality. The proposed feature-split algorithm is compared to existing methods by both numerical simulations and applications to real data examples. The numerical comparisons suggest that the proposed method works well for ultrahigh dimensions, while the linear programming solver and alternating direction method of multiplier (ADMM) algorithm may fail for such high dimensions.- 1 December 2022
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 32 (3) , 1074-1082
Regularized Linear Programming Discriminant Rule with Folded Concave Penalty for Ultrahigh-Dimensional Data
We propose the regularized linear programming discriminant (LPD) rule with folded concave penalty in the ultrahigh-dimensional regime. We use the local linear approximation (LLA) algorithm to redirect the model with folded concave penalty to a weighted model. The strong oracle property of the solution constructed by the one-step local linear approximation (LLA) algorithm is verified. In addition, we propose efficient and parallelizable algorithms based on feature space split to address the computational challenges due to ultrahigh dimensionality. The proposed feature-split algorithm is compared to existing methods by both numerical simulations and applications to real data examples. The numerical comparisons suggest that the proposed method works well for ultrahigh dimensions, while the linear programming solver and alternating direction method of multiplier (ADMM) algorithm may fail for such high dimensions.- Open Access
- 7 July 2022
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 117 (540) , 1642-1655
Causal Structural Learning on MPHIA Individual Dataset
The Population-based HIV Impact Assessment (PHIA) is an ongoing project that conducts nationally representative HIV-focused surveys for measuring national and regional progress toward UNAIDS’ 90-90-90 targets, the primary strategy to end the HIV epidemic. We believe the PHIA survey offers a unique opportunity to better understand the key factors that drive the HIV epidemics in the most affected countries in sub-Saharan Africa. In this article, we propose a novel causal structural learning algorithm to discover important covariates and potential causal pathways for 90-90-90 targets. Existing constrained-based causal structural learning algorithms are quite aggressive in edge removal. The proposed algorithm preserves more information about important features and potential causal pathways. It is applied to the Malawi PHIA (MPHIA) data set and leads to interesting results. For example, it discovers age and condom usage to be important for female HIV awareness; the number of sexual partners to be important for male HIV awareness; and knowing the travel time to HIV care facilities leads to a higher chance of being treated for both females and males. We further compare and validate the proposed algorithm using BIC and using Monte Carlo simulations, and show that the proposed algorithm achieves improvement in true positive rates in important feature discovery over existing algorithms.
- 7 July 2022
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 117 (540) , 1642-1655
Open AccessCausal Structural Learning on MPHIA Individual Dataset
The Population-based HIV Impact Assessment (PHIA) is an ongoing project that conducts nationally representative HIV-focused surveys for measuring national and regional progress toward UNAIDS’ 90-90-90 targets, the primary strategy to end the HIV epidemic. We believe the PHIA survey offers a unique opportunity to better understand the key factors that drive the HIV epidemics in the most affected countries in sub-Saharan Africa. In this article, we propose a novel causal structural learning algorithm to discover important covariates and potential causal pathways for 90-90-90 targets. Existing constrained-based causal structural learning algorithms are quite aggressive in edge removal. The proposed algorithm preserves more information about important features and potential causal pathways. It is applied to the Malawi PHIA (MPHIA) data set and leads to interesting results. For example, it discovers age and condom usage to be important for female HIV awareness; the number of sexual partners to be important for male HIV awareness; and knowing the travel time to HIV care facilities leads to a higher chance of being treated for both females and males. We further compare and validate the proposed algorithm using BIC and using Monte Carlo simulations, and show that the proposed algorithm achieves improvement in true positive rates in important feature discovery over existing algorithms.
- 1 March 2022
- Published by Elsevier in Journal of Multivariate Analysis
- Vol. 188
An overview of tests on high-dimensional means
- 1 March 2022
- Published by Elsevier in Journal of Multivariate Analysis
- Vol. 188
An overview of tests on high-dimensional means
- 1 November 2020
- Published by American Dairy Science Association in Journal of Dairy Science
- Vol. 103 (11) , 9958-9968
Growth kinetics of Staphylococcus aureus and background microorganisms in camel milk
Staphylococcus aureus is a common foodborne pathogen that is ubiquitous in nature. Consumption of contaminated foods, such as dairy products, can lead to food poisoning caused by heat-stable staphylococcal toxins that are not easily destroyed during pasteurization. The objective of this study was to investigate the growth kinetics of S. aureus and background microorganisms in camel milk stored at different temperatures between 8 and 43°C using one-step kinetic analysis to estimate the kinetic parameters from the observed growth curves. The growth of S. aureus showed apparent lag, exponential, and stationary phases, whereas no or negligible lag phase was observed for background microorganisms. Data analysis showed that the estimated minimum, optimum, and maximum growth temperatures were 5.9, 42.0, and 49.2°C for S. aureus, and 3.0, 38.6, and 49.2°C for the background microorganisms, respectively. The estimated optimum specific growth rate was higher for S. aureus (1.24 h-1) than for background microorganisms (0.995 h-1). This study found that camel milk may inhibit the growth of S. aureus, as it exhibits a lower specific growth rate than that in cow milk or cooked potato. It also has a longer lag phase than that in cow milk at comparable temperature ranges. This unique property is probably related to the presence of some antimicrobial compounds naturally occurring in camel milk. Validation of kinetic parameters and models showed that the root mean square error of prediction was only 0.5 log cfu/mL for S. aureus and background microorganisms, suggesting that the models are reasonably accurate. These models can be used for conducting risk assessments of S. aureus and predicting the general microbiological shelf life of camel milk to prevent foodborne staphylococcal poisoning.
- 1 November 2020
- Published by American Dairy Science Association in Journal of Dairy Science
- Vol. 103 (11) , 9958-9968
Growth kinetics of Staphylococcus aureus and background microorganisms in camel milk
Staphylococcus aureus is a common foodborne pathogen that is ubiquitous in nature. Consumption of contaminated foods, such as dairy products, can lead to food poisoning caused by heat-stable staphylococcal toxins that are not easily destroyed during pasteurization. The objective of this study was to investigate the growth kinetics of S. aureus and background microorganisms in camel milk stored at different temperatures between 8 and 43°C using one-step kinetic analysis to estimate the kinetic parameters from the observed growth curves. The growth of S. aureus showed apparent lag, exponential, and stationary phases, whereas no or negligible lag phase was observed for background microorganisms. Data analysis showed that the estimated minimum, optimum, and maximum growth temperatures were 5.9, 42.0, and 49.2°C for S. aureus, and 3.0, 38.6, and 49.2°C for the background microorganisms, respectively. The estimated optimum specific growth rate was higher for S. aureus (1.24 h-1) than for background microorganisms (0.995 h-1). This study found that camel milk may inhibit the growth of S. aureus, as it exhibits a lower specific growth rate than that in cow milk or cooked potato. It also has a longer lag phase than that in cow milk at comparable temperature ranges. This unique property is probably related to the presence of some antimicrobial compounds naturally occurring in camel milk. Validation of kinetic parameters and models showed that the root mean square error of prediction was only 0.5 log cfu/mL for S. aureus and background microorganisms, suggesting that the models are reasonably accurate. These models can be used for conducting risk assessments of S. aureus and predicting the general microbiological shelf life of camel milk to prevent foodborne staphylococcal poisoning.
- Open Access
- 13 March 2019
- Published by The Open Journal in Journal of Open Source Software
- Vol. 4 (35)
JuliaCall: an R package for seamless integration between R and Julia
- 13 March 2019
- Published by The Open Journal in Journal of Open Source Software
- Vol. 4 (35)
Open AccessJuliaCall: an R package for seamless integration between R and Julia
- 31 January 2012
- Published by Springer Nature in Biological Trace Element Research
- Vol. 148 (1) , 117-121
The Influence of Fluoride on the Expression of Inhibitors of Wnt/β-Catenin Signaling Pathway in Rat Skin Fibroblast Cells
The effective therapy of fluoride-induced bone diseases requires an understanding of the mechanism of the disorders. Changes in the inhibitors of the Wnt/β-catenin pathway, Dickkopf-1 (Dkk-1) and Sclerostin (SOST), were studied in supernatants harvested from rat skin fibroblasts cultured with varied doses of fluoride. The contents of SOST and Dkk-1 in fibroblast supernatants were assessed at four exposure time-points and investigated by using the method of ELISA. Compared to the relevant controls (0 mg F−/L), a significant decrease of the concentrations of SOST and Dkk-1 was observed as the fluoride concentration increased. Compared to the relevant time controls (24 h), a significant decrease of the concentrations of SOST and Dkk-1 was observed with the extension of time. Our results suggest that the Wnt/β-catenin pathway inhibitors Dkk-1 and SOST play an important role in skeletal fluorosis. They can be used as important indications for diagnosing bone metabolism changes caused by fluoride exposure and therapeutic targets in diseases resulting from fluoride exposure.
- 31 January 2012
- Published by Springer Nature in Biological Trace Element Research
- Vol. 148 (1) , 117-121
The Influence of Fluoride on the Expression of Inhibitors of Wnt/β-Catenin Signaling Pathway in Rat Skin Fibroblast Cells
The effective therapy of fluoride-induced bone diseases requires an understanding of the mechanism of the disorders. Changes in the inhibitors of the Wnt/β-catenin pathway, Dickkopf-1 (Dkk-1) and Sclerostin (SOST), were studied in supernatants harvested from rat skin fibroblasts cultured with varied doses of fluoride. The contents of SOST and Dkk-1 in fibroblast supernatants were assessed at four exposure time-points and investigated by using the method of ELISA. Compared to the relevant controls (0 mg F−/L), a significant decrease of the concentrations of SOST and Dkk-1 was observed as the fluoride concentration increased. Compared to the relevant time controls (24 h), a significant decrease of the concentrations of SOST and Dkk-1 was observed with the extension of time. Our results suggest that the Wnt/β-catenin pathway inhibitors Dkk-1 and SOST play an important role in skeletal fluorosis. They can be used as important indications for diagnosing bone metabolism changes caused by fluoride exposure and therapeutic targets in diseases resulting from fluoride exposure.