Article
Biology
Peijie Wang, Danning Li, Jianguo Sun
Summary: The paper discusses regression analysis of left-truncated failure time data, proposing a pairwise pseudo-likelihood approach and demonstrating its efficiency and feasibility through a simulation study.
Article
Statistics & Probability
Sangbum Choi, Xuelin Huang
Summary: This article examines nonparametric maximum likelihood estimation of semiparametric transformation models for doubly-censored data in medical studies, such as HIV/AIDS clinical trials. The estimator is consistent and asymptotically normal, with statistical inferences conveniently made from the inverse of the observed information matrix. Simulation studies show that the NPMLE performs well even under heavy censoring and outperforms methods based on estimating functions in terms of efficiency.
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
(2021)
Article
Statistics & Probability
Liang Zhu, Xingwei Tong, Dingjiao Cai, Yimei Li, Ryan Sun, Deo K. Srivastava, Melissa M. Hudson
Summary: This article discusses regression analysis of mixed interval-censored failure time data and proposes a maximum likelihood estimation procedure for the proportional odds regression model. Extensive simulation studies show that the method works well for many practical situations. The approach is then applied to examine the impact of age at cranial radiation therapy on risk of growth hormone deficiency in long-term survivors of childhood cancer.
JOURNAL OF APPLIED STATISTICS
(2021)
Article
Health Care Sciences & Services
Haolun Shi, Da Ma, Mirza Faisal Beg, Jiguo Cao
Summary: This study proposes a functional mixture cure rate model for predicting the conversion to Alzheimer's disease from sparse biomarker trajectories in patients with mild cognitive impairment, utilizing functional principal component analysis to extract functional features from irregularly sampled trajectories and applying the expectation-maximization algorithm for parameter estimation. The method's estimation accuracy is evaluated through simulation studies and applied to the Alzheimer's Disease Neuroimaging Initiative dataset.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2022)
Article
Health Care Sciences & Services
Liuquan Sun, Shuwei Li, Lianming Wang, Xinyuan Song
Summary: A two-component mixture cure model approach is proposed for the analysis of partly interval-censored data, consisting of both exactly observed and interval-censored observations on the failure time of interest. The cured probability is described using a logistic model, while the latent failure time distribution for uncured subjects is modeled using a proportional hazards model. The method utilizes maximum likelihood estimation and a new expectation-maximization algorithm for implementation, with established asymptotic properties of resulting estimators and examination of finite sample performance through simulation studies.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Health Care Sciences & Services
Mengzhu Yu, Yanqin Feng, Ran Duan, Jianguo Sun
Summary: This study proposes an estimating equation-based approach for regression analysis of multivariate interval-censored data from the additive hazards model, allowing for informative censoring. A simulation study confirms the effectiveness of the method in practical situations. The proposed approach is also successfully applied to real data.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2022)
Article
Statistics & Probability
Mingyue Du, Jianguo Sun
Summary: Variable selection for interval-censored failure time data has recently gained significant attention in both method developments and practical applications. Interval-censored data, where the failure time is only known to lie within an interval, are common in various fields and more research is needed in this relatively new but important topic.
INTERNATIONAL STATISTICAL REVIEW
(2022)
Article
Multidisciplinary Sciences
Yan Chen, Yulu Zhao
Summary: A novel penalty approach for the proportional hazards model under interval-censored failure time data structure is discussed, which approximates information criterion by smoothing the l(0) norm. This method eliminates the need for tedious hyperparameter tuning, improves efficiency of model fitting, and guarantees properties of continuity, sparsity, and unbiasedness for penalties. The proposed sparse estimation method shows high accuracy and efficiency in numerical results, and key factors affecting child mortality are identified using this method on Nigerian children data.
Article
Statistics & Probability
Yuqing Ma, Peijie Wang, Jianguo Sun
Summary: Estimation of compiler causal treatment effects has been discussed, but limited literature exists for interval-censored failure time data. Informative interval censoring can make analysis more challenging, and not considering it can lead to biased or misleading results. To address this, we propose an estimated sieve maximum likelihood approach with instrumental variables. The resulting estimators have established asymptotic properties and the method shows good performance in simulation and real data.
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS
(2023)
Article
Health Care Sciences & Services
Sean M. Devlin, Glenn Heller
Summary: The manuscript introduces a new method for estimating concordance probability in time-to-event models, which requires input from analysts to determine separable survival regions for comparing risk scores between individuals. This method is analogous to clinically defined subgroups used for binary outcome area under the curve estimates.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuqing Ma, Peijie Wang, Jianguo Sun
Summary: This paper addresses the problem of assessing causal treatment effect in randomized survival studies with non-compliance and time-to-event outcomes. It focuses on case-cohort studies where covariates are too expensive to measure for the entire cohort and the disease rate is low. Additionally, only interval-censored data is available for the failure event, which lacks an established estimation procedure. To solve this problem, a sieve inverse probability weighting estimation procedure is proposed and the resulting estimators are shown to be consistent and asymptotically normal. Simulation study and application to a breast cancer screening study validate the performance of the proposed method.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2023)
Article
Statistics & Probability
Bo Zhao, Shuying Wang, Chunjie Wang
Summary: The paper introduces the application of the proportional odds model in survival analysis and proposes a variable selection method based on this model. The method takes into account special cases of failure time data and addresses the issue of dependent censoring. Numerical studies and practical applications demonstrate the good performance of the proposed method.
STATISTICAL PAPERS
(2023)
Article
Mathematical & Computational Biology
Lu Wang, Lianming Wang
Summary: This article investigates the Proportional Odds (PO) model and presents a novel estimation approach using an Expectation-Maximization (EM) algorithm for analyzing arbitrarily censored survival data. The proposed EM algorithm is robust, easy to implement, converges fast, and provides variance estimates of regression parameters in closed form. The method shows excellent performance in estimating regression parameters and baseline survival function in simulation studies and analysis of real-life datasets.
STATISTICS IN MEDICINE
(2021)
Article
Statistics & Probability
Bo Zhao, Shuying Wang, Chunjie Wang
Summary: This article proposes a new frailty-based generalized estimating equation (GEE) method for proportional hazards (PH) model with informative interval-censored failure time data. The proposed method can provide an unbiased estimator of the cumulative hazards function. The performance of the method is assessed through extensive simulation study and an application to an AIDS clinical trial dataset.
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
(2023)
Article
Computer Science, Interdisciplinary Applications
Xiaoyu Liu, Liming Xiang
Summary: This study proposes a more flexible class of generalized accelerated hazards mixture cure models for analyzing interval-censored failure times. A sieve maximum likelihood estimation method is used to approximate the unknown cumulative baseline hazard function with B-splines. Simulation results demonstrate satisfactory performance of the proposed method in finite samples.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
