Mai Zhou
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
Mai Zhou has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Arne Bathke
Department of Statistics, University of Kentucky, 875 Patterson Office Tower, Lexington, KY 40506-0027, USA
2 shared publications - Mi-Ok Kim
Department of Epidemiology and Biostatistics, University of California, San Francisco, California
2 shared publications - Arnold Stromberg
Department of Statistics, University of Kentucky, Lexington, KY, USA
1 shared publication - Christopher P. Saunders
Document Forensics Laboratory (MS 1G8), George Mason University, 4400 University Drive, Fairfax, VA 22030, USA
1 shared publication - Gang Li
Department of Biostatistics University of California at Los Angeles Los Angeles CA USA
1 shared publication - Haiyan Su
Montclair State University
1 shared publication
Latest Publications
- Open Access
Consistency of survival tree and forest models: splitting bias and correction
Random survival forest and survival trees are popular models in statistics and machine learning. However, there is a lack of general understanding regarding consistency, splitting rules and influence of the censoring mechanism. In this paper, we investigate the statistical properties of existing methods from several interesting perspectives. First, we show that traditional splitting rules with censored outcomes rely on a biased estimation of the within-node failure distribution. To exactly quantify this bias, we develop a concentration bound of the within-node estimation based on non i.i.d. samples and apply it to the entire forest. Second, we analyze the entanglement between the failure and censoring distributions caused by univariate splits, and show that without correcting the bias at an internal node, survival tree and forest models can still enjoy consistency under suitable conditions. In particular, we demonstrate this property under two cases: a finite-dimensional case where the splitting variables and cutting points are chosen randomly, and a high-dimensional case where the covariates are weakly correlated. Our results can also degenerate into an independent covariate setting, which is commonly used in the random forest literature for high-dimensional sparse models. However, it may not be avoidable that the convergence rate depends on the total number of variables in the failure and censoring distributions. Third, we propose a new splitting rule that compares bias-corrected cumulative hazard functions at each internal node. We show that the rate of consistency of this new model depends only on the number of failure variables, which improves from non-bias-corrected versions. We perform simulation studies to confirm that this can substantially benefit the prediction error.
Open AccessConsistency of survival tree and forest models: splitting bias and correction
Random survival forest and survival trees are popular models in statistics and machine learning. However, there is a lack of general understanding regarding consistency, splitting rules and influence of the censoring mechanism. In this paper, we investigate the statistical properties of existing methods from several interesting perspectives. First, we show that traditional splitting rules with censored outcomes rely on a biased estimation of the within-node failure distribution. To exactly quantify this bias, we develop a concentration bound of the within-node estimation based on non i.i.d. samples and apply it to the entire forest. Second, we analyze the entanglement between the failure and censoring distributions caused by univariate splits, and show that without correcting the bias at an internal node, survival tree and forest models can still enjoy consistency under suitable conditions. In particular, we demonstrate this property under two cases: a finite-dimensional case where the splitting variables and cutting points are chosen randomly, and a high-dimensional case where the covariates are weakly correlated. Our results can also degenerate into an independent covariate setting, which is commonly used in the random forest literature for high-dimensional sparse models. However, it may not be avoidable that the convergence rate depends on the total number of variables in the failure and censoring distributions. Third, we propose a new splitting rule that compares bias-corrected cumulative hazard functions at each internal node. We show that the rate of consistency of this new model depends only on the number of failure variables, which improves from non-bias-corrected versions. We perform simulation studies to confirm that this can substantially benefit the prediction error.
- 1 January 2018
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 29 (1) , 371-386
COMPARISON OF EXTENDED EMPIRICAL LIKELIHOOD METHODS: SIZE AND SHAPE OF TEST BASED CONFIDENCE REGIONS
- 1 January 2018
- Published by Statistica Sinica (Institute of Statistical Science) in Statistica Sinica
- Vol. 29 (1) , 371-386
COMPARISON OF EXTENDED EMPIRICAL LIKELIHOOD METHODS: SIZE AND SHAPE OF TEST BASED CONFIDENCE REGIONS
- 3 March 2015
- Published by Springer Nature in Computational Statistics
- Vol. 30 (4) , 1097-1109
A recursive formula for the Kaplan–Meier estimator with mean constraints and its application to empirical likelihood
- 3 March 2015
- Published by Springer Nature in Computational Statistics
- Vol. 30 (4) , 1097-1109
A recursive formula for the Kaplan–Meier estimator with mean constraints and its application to empirical likelihood
- 12 March 2011
- Published by Springer Nature in Lifetime Data Analysis
- Vol. 17 (4) , 533-551
Semi-parametric hybrid empirical likelihood inference for two-sample comparison with censored data
Two-sample comparison problems are often encountered in practical projects and have widely been studied in literature. Owing to practical demands, the research for this topic under special settings such as a semiparametric framework have also attracted great attentions. Zhou and Liang (Biometrika 92:271-282, 2005) proposed an empirical likelihood-based semi-parametric inference for the comparison of treatment effects in a two-sample problem with censored data. However, their approach is actually a pseudo-empirical likelihood and the method may not be fully efficient. In this study, we develop a new empirical likelihood-based inference under more general framework by using the hazard formulation of censored data for two sample semi-parametric hybrid models. We demonstrate that our empirical likelihood statistic converges to a standard chi-squared distribution under the null hypothesis. We further illustrate the use of the proposed test by testing the ROC curve with censored data, among others. Numerical performance of the proposed method is also examined.
- 12 March 2011
- Published by Springer Nature in Lifetime Data Analysis
- Vol. 17 (4) , 533-551
Semi-parametric hybrid empirical likelihood inference for two-sample comparison with censored data
Two-sample comparison problems are often encountered in practical projects and have widely been studied in literature. Owing to practical demands, the research for this topic under special settings such as a semiparametric framework have also attracted great attentions. Zhou and Liang (Biometrika 92:271-282, 2005) proposed an empirical likelihood-based semi-parametric inference for the comparison of treatment effects in a two-sample problem with censored data. However, their approach is actually a pseudo-empirical likelihood and the method may not be fully efficient. In this study, we develop a new empirical likelihood-based inference under more general framework by using the hazard formulation of censored data for two sample semi-parametric hybrid models. We demonstrate that our empirical likelihood statistic converges to a standard chi-squared distribution under the null hypothesis. We further illustrate the use of the proposed test by testing the ROC curve with censored data, among others. Numerical performance of the proposed method is also examined.
- 18 February 2010
- Published by Springer Nature in Annals of the Institute of Statistical Mathematics
- Vol. 63 (5) , 1005-1018
Full likelihood inferences in the Cox model: an empirical likelihood approach
- 18 February 2010
- Published by Springer Nature in Annals of the Institute of Statistical Mathematics
- Vol. 63 (5) , 1005-1018
Full likelihood inferences in the Cox model: an empirical likelihood approach
- 1 March 2009
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 139 (3) , 814-827
Combined multiple testing by censored empirical likelihood
- 1 March 2009
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 139 (3) , 814-827
Combined multiple testing by censored empirical likelihood
- Open Access
- 2 July 2008
- Published by Springer Nature in BMC Bioinformatics
- Vol. 9 (1) , 300
A novel application of quantile regression for identification of biomarkers exemplified by equine cartilage microarray data
Identification of biomarkers among thousands of genes arrayed for disease classification has been the subject of considerable research in recent years. These studies have focused on disease classification, comparing experimental groups of effected to normal patients. Related experiments can be done to identify tissue-restricted biomarkers, genes with a high level of expression in one tissue compared to other tissue types in the body.
- 2 July 2008
- Published by Springer Nature in BMC Bioinformatics
- Vol. 9 (1) , 300
Open AccessA novel application of quantile regression for identification of biomarkers exemplified by equine cartilage microarray data
Identification of biomarkers among thousands of genes arrayed for disease classification has been the subject of considerable research in recent years. These studies have focused on disease classification, comparing experimental groups of effected to normal patients. Related experiments can be done to identify tissue-restricted biomarkers, genes with a high level of expression in one tissue compared to other tissue types in the body.
- 21 November 2007
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 77 (12) , 1033-1042
Computation of the empirical likelihood ratio from censored data
The empirical likelihood ratio method is a general nonparametric inference procedure that has many desirable properties. Recently, the procedure has been generalized to several settings including testing of weighted means with right-censored data. However, the computation of the empirical likelihood ratio with censored data and other complex settings is often nontrivial. We propose to use a sequential quadratic programming (SQP) method to solve the computational problem. We introduce several auxiliary variables so that the computation of SQP is greatly simplified. Examples of the computation with null hypothesis concerning the weighted mean are presented for right- and interval-censored data.
- 21 November 2007
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 77 (12) , 1033-1042
Computation of the empirical likelihood ratio from censored data
The empirical likelihood ratio method is a general nonparametric inference procedure that has many desirable properties. Recently, the procedure has been generalized to several settings including testing of weighted means with right-censored data. However, the computation of the empirical likelihood ratio with censored data and other complex settings is often nontrivial. We propose to use a sequential quadratic programming (SQP) method to solve the computational problem. We introduce several auxiliary variables so that the computation of SQP is greatly simplified. Examples of the computation with null hypothesis concerning the weighted mean are presented for right- and interval-censored data.
- 7 March 2007
- Published by Elsevier in Journal of Multivariate Analysis
- Vol. 99 (4) , 649-664
Empirical likelihood analysis of the Buckley–James estimator
- 7 March 2007
- Published by Elsevier in Journal of Multivariate Analysis
- Vol. 99 (4) , 649-664
Empirical likelihood analysis of the Buckley–James estimator
- 1 June 2005
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 92 (2) , 492-498
Empirical likelihood analysis of the rank estimator for the censored accelerated failure time model
We use the empirical likelihood method to derive a test and thus a confidence interval based on the rank estimators of the regression coefficient in the accelerated failure time model. Standard chi-squared distributions are used to calculate the p-value and to construct the confidence interval. Simulations and examples show that the chi-squared approximation to the distribution of the log empirical likelihood ratio performs well, and has some advantages over the existing methods.
- 1 June 2005
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 92 (2) , 492-498
Empirical likelihood analysis of the rank estimator for the censored accelerated failure time model
We use the empirical likelihood method to derive a test and thus a confidence interval based on the rank estimators of the regression coefficient in the accelerated failure time model. Standard chi-squared distributions are used to calculate the p-value and to construct the confidence interval. Simulations and examples show that the chi-squared approximation to the distribution of the log empirical likelihood ratio performs well, and has some advantages over the existing methods.