Article
Mathematical & Computational Biology
Meng Liu, Yang Zhao
Summary: In this study, new WGEEs for missing at random data were proposed, with a unified approach to improve estimation efficiency. The proposed method showed consistent and more efficient results in simulation studies with both continuous response and binary response data.
STATISTICS IN MEDICINE
(2022)
Article
Computer Science, Interdisciplinary Applications
Youjun Huang, Jianxin Pan
Summary: Modeling longitudinal binary data with constraints on the correlation coefficients is achieved by a novel joint GEE method, which shows good performance in simulation studies even under misspecified covariance structures. The proposed method allows for simultaneous modeling of mean and within-subject correlation coefficients, taking into account the upper bound of the correlation coefficients.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Public, Environmental & Occupational Health
Michael E. Griswold, Rajesh Talluri, Xiaoqian Zhu, Dan Su, Jonathan Tingle, Rebecca F. Gottesman, Jennifer Deal, Andreea M. Rawlings, Thomas H. Mosley, B. Gwen Windham, Karen Bandeen-Roche
Summary: This article discusses the common issue of missing data in longitudinal studies and recommends the shared-parameter model (SPM) as a more widely used approach. The article provides reproducible research code and data to facilitate the use of SPMs in practice and teaching in epidemiology, biostatistics, and data science, aiming to increase understanding and usage of these methods.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2021)
Article
Statistics & Probability
Li-E Cui, Puying Zhao, Niansheng Tang
Summary: The estimation of propensity score (PS) function in missing data analysis is challenging. In this study, we propose a series estimation method to estimate the PS function and introduce generalized empirical likelihood (GEL) estimators to obtain efficient parameter estimates.
JOURNAL OF MULTIVARIATE ANALYSIS
(2022)
Article
Biochemical Research Methods
Han Sun, Xiaoyun Huang, Ban Huo, Yuting Tan, Tingting He, Xingpeng Jiang
Summary: The study developed a novel method called aGEEMIHC to detect sparse microbial association signals in longitudinal microbiome data using generalized estimating equations. Simulation experiments showed that aGEEMiHC achieved superior statistical power and stability for different types of host phenotypes.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Mathematical & Computational Biology
Youjun Huang, Jianxin Pan
Summary: The paper proposes a PJGEE method based on SCAD and LASSO for modeling the mean and correlations of longitudinal binary data, along with variable selection. Simulation studies show that the method outperforms existing PGEE methods in terms of variable selection consistency and parameter estimation accuracy. Analysis on a real data set further confirms the effectiveness of the method.
BIOMETRICAL JOURNAL
(2022)
Article
Health Care Sciences & Services
Zhiping Qiu, Huijuan Ma, Jianwei Chen, Gregg E. Dinse
Summary: The paper discusses the quantile regression model for survival data with missing censoring indicators, proposes two weighted estimating equations based on the augmented inverse probability weighting technique, and establishes asymptotic properties of the resultant estimators and resampling-based inference procedures. The performance of the proposed approaches is investigated in simulation studies and a real data application.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Biology
Tsubasa Ito, Shonosuke Sugasawa
Summary: In this paper, a grouped GEE analysis method is proposed to address the heterogeneity in regression coefficients in longitudinal data modeling. This method divides subjects into groups and assumes that subjects within the same group share the same regression coefficient. An algorithm for grouping subjects and estimating regression coefficients simultaneously is provided, and the asymptotic properties of the estimator are shown.
Article
Physics, Multidisciplinary
Maximilian Kertel, Markus Pauly
Summary: In this work, we rigorously apply the Expectation Maximization algorithm to determine the marginal distributions and dependence structure in a Gaussian copula model with missing data. We show how to avoid prior assumptions on the marginals through semiparametric modeling and explain how expert knowledge can be incorporated. Simulation results demonstrate that the distribution learned using this algorithm is closer to the true distribution than existing methods, and the inclusion of domain knowledge provides benefits.
Article
Computer Science, Interdisciplinary Applications
P. Mohan Shankar
Summary: The author has incorporated data analytics into the probability course for engineering students. By exploring missing and incomplete data related to the coronavirus pandemic, the author expanded the activities in data analytics. A demo was created to examine the association between the transformation of random variables and truncation, and it was used as a basis for student assignments. The results suggest that the course can be extended to provide training in contemporary topics in data analytics.
COMPUTER APPLICATIONS IN ENGINEERING EDUCATION
(2022)
Article
Mathematical & Computational Biology
Chun-Shu Chen, Chung-Wei Shen
Summary: This study explores the selection of appropriate models and covariates in count data with excess zeros, using various models and weighted generalized estimating equations to estimate parameters and alleviate biases from model assumptions. Additionally, a model selection criterion based on expected weighted quadratic loss without distribution assumptions is proposed, along with discussion on the selection effects of percentages of excess zeros and missingness through simulation studies and a real data example.
STATISTICS IN MEDICINE
(2022)
Article
Mathematics, Interdisciplinary Applications
Yi Xiong, W. John Braun, X. Joan Hu
Summary: The study proposes estimating duration distribution using the first-hitting-time model, establishing consistency and weak convergence of the distribution estimator, showing the proposed estimator to be more efficient than traditional methods in simulations.
LIFETIME DATA ANALYSIS
(2021)
Article
Engineering, Electrical & Electronic
Francesco Grassi, Angelo Coluccia
Summary: Heavy-tailed random samples and their aggregate are common in various signal processing applications. Modeling these data with the Pareto distribution is attractive but may lead to infinite variance and mean, which is not physically plausible. In practice, samples are always bounded due to clipping during signal acquisition or intentional censoring at the processing stage.
Article
Health Care Sciences & Services
Lauren J. Beesley, Irina Bondarenko, Michael R. Elliot, Allison W. Kurian, Steven J. Katz, Jeremy M. G. Taylor
Summary: This paper describes how to generalize the sequential regression multiple imputation procedure to handle non-random missingness when missingness may depend on other variables. The method reduces bias in the final analysis compared to standard techniques, using approximation strategies involving inclusion of an offset in the imputation model.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Mathematical & Computational Biology
Wenwen Li, Huijuan Ma, David Faraggi, Gregg E. Dinse
Summary: The article investigates the modeling and inference of a family of generalized MRL models for right-censored survival data with missing censoring indicators. Augmented inverse probability weighted estimating equation approaches are developed to estimate the model parameters, with the non-missingness probability and the conditional probability of an uncensored observation estimated using parametric or nonparametric techniques. The asymptotic properties of the proposed estimators are established and their finite sample performance is evaluated through extensive simulation studies. An application to brain cancer data is presented to illustrate the proposed methods.
STATISTICS IN MEDICINE
(2023)
Article
Surgery
Jacob Y. Katsnelson, Richard Tyrell, Murad J. Karadsheh, Ely Manstein, Brian Egleston, Mengying Deng, Pablo A. Baltodano, M. Shuja Shafqat, Sameer A. Patel
Summary: In head and neck reconstruction, myocutaneous pedicled flaps are associated with higher overall short-term postoperative complications compared with free flaps, but do not significantly impact hospital readmission, reoperation, or length-of-stay.
JOURNAL OF RECONSTRUCTIVE MICROSURGERY
(2022)
Article
Surgery
Nicholas A. Elmer, Sthefano Araya, Juliet Panichella, Brian Egleston, Mengying Deng, Sameer A. Patel
Summary: This study aimed to understand the temporal pattern and risk factors associated with lower extremity free flap failure. It found a reoperation rate of 14.5% within the first 30 postoperative days, with patients with vascular indications having the highest rate. The rate of reoperation was highest during the first 2 days postoperative and significantly decreased afterwards. African American race, malignant tumors, prosthetic/implant complications, and wound/infectious indications were significant predictors for reoperation.
ANNALS OF PLASTIC SURGERY
(2023)
Letter
Oncology
Benjamin G. Carlisle, Donna L. Coffman, Brian L. Egleston, Maia Salholz-Hillel
ANNALS OF SURGICAL ONCOLOGY
(2023)
Article
Psychology, Clinical
Bradley N. Collins, Stephen J. Lepore, Brian L. Egleston
Summary: This study aimed to examine the effectiveness of the BLiSS multilevel intervention in promoting smoking cessation among low-income maternal smokers and its impact on smoking relapse rates over a 12-month period. The results showed that mothers who received the intervention were more likely to eliminate their children's tobacco smoke exposure within three months, which was significantly associated with long-term smoking abstinence.
JOURNAL OF BEHAVIORAL MEDICINE
(2023)
Article
Oncology
Brian L. Egleston, Richard J. Bleicher, Carolyn Y. Fang, Thomas J. Galloway, Slobodan Vucetic
Summary: Additional evaluations and second opinions before breast cancer surgery may improve care, but could cause detrimental delays. This study investigates the timing of surgical delays associated with survival benefits and potential harm. It found that quick new patient visits have a protective association with breast cancer mortality, but substantial delays may increase mortality in older patients. Similarly, delays in medical oncologist and surgeon visits can also have negative impacts on outcomes.
Article
Surgery
Sthefano Araya, Theresa K. K. Webster, Brian Egleston, Grace M. M. Amadio, Juliet C. C. Panichella, Nicholas A. A. Elmer, Sameer A. A. Patel
Summary: This study reviewed the impact of ERAS implementation on the length of stay (LOS) in patients undergoing DIEP free-flap breast reconstruction. The results showed that the implementation of ERAS protocols led to a significant decrease in LOS and supported safe discharge on postoperative days 2-3.
ANNALS OF PLASTIC SURGERY
(2023)
Article
Oncology
Madison Kilbride, Brian L. Egleston, Wendy K. Chung, Olufunmilayo Olopade, Kara N. Maxwell, Payal Shah, Jane E. Churpek, Linda Fleisher, Mary Beth Terry, Dominique Fetzer, Jill Bennett Gaieski, Jessica Bulafka, Aileen Espinal, Kelsey Karpink, Sarah Walser, Davone Singleton, Monica Palese, Ilona Siljander, Amanda Brandt, Dana Clark, Carrie Koval, Julia Wynn, Jessica M. Long, Danielle Mckenna, Jacquelyn Powers, Sarah Nielsen, Susan M. Domchek, Katherine L. Nathanson, Angela R. Bradbury
Summary: The study showed high interest in web-based predisclosure education for returning genetic research results, but it did not increase the uptake of results. There were no negative patient-reported outcomes with web education, indicating that it is a viable alternative delivery model for reducing burdens and costs of returning genetic research results.
JOURNAL OF CLINICAL ONCOLOGY
(2023)
Article
Public, Environmental & Occupational Health
Amy H. Auchincloss, Francesca Mucciaccio, Carolyn Y. Fang, Dominic A. Ruggiero, Jana A. Hirsch, Julia Zhong, Minzi Li, Brian L. Egleston, Marilyn Tseng
Summary: This study examined the relationship between neighborhood social composition, gentrification, and acculturation stress among first-generation Chinese immigrants. The findings showed that Chinese immigrants living in neighborhoods with a higher proportion of Chinese immigrants and higher wealth experienced lower acculturation stress, while gentrification had no impact.
SSM-POPULATION HEALTH
(2023)
Article
Health Care Sciences & Services
Margaret L. Longacre, Marcin Chwistek, Cynthia Keleher, Mark Siemon, Brian L. Egleston, Molly Collins, Carolyn Y. Fang
Summary: The study demonstrates the usability and satisfaction of a patient-caregiver portal system in engaging caregivers systematically. The system allows patients to specify their caregiver and communication preferences, connects caregivers to a unique portal page, and provides electronic notifications to the care team. The findings highlight the need for further research on caregivers of patients with different illnesses.
JMIR HUMAN FACTORS
(2023)
Meeting Abstract
Oncology
Mary Daly, Brian Egleston, Kaitlyn Lew, Lisa Bealin, Alexander Husband, Jill Stopfe, Pawel Przybysz, Olga Tchuvatkina, Yu-Ning Wong, Judy Garber, Timothy Rebbeck
Meeting Abstract
Oncology
Brian Egleston, Mary Daly, Kaitlyn Lew, Lisa Bealin, Alexander Husband, Jill Stopfer, Pawel Przybysz, Olga Tchuvatkina, Yu-Ning Wong, Judy Garber, Timothy Rebbeck
Article
Social Sciences, Mathematical Methods
Brian L. Egleston, Ashis Kumar Chanda, Tian Bai, Carolyn Y. Fang, Richard J. Bleicher, Slobodan Vucetic
Summary: Identification of procedures using medical codes for medical claims research is challenging. Pointwise Mutual Information can be used to find associated codes. In a study on racial differences in breast cancer outcomes, treatment definitions were identified using the Pointwise Mutual Information statistic. The study found that survival disparities between Black and White women were completely eliminated with augmented treatment definitions.
METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES
(2023)
Meeting Abstract
Oncology
Marilyn Tseng, Brian Egleston, Julia Zhong, Minzi Li, Carolyn Fang
CANCER EPIDEMIOLOGY BIOMARKERS & PREVENTION
(2023)
Meeting Abstract
Oncology
Ella Batterson, Marilyn Tseng, Emily C. Walton, Brian Egleston, Julia Zhong, Minzi Li, Carolyn Fang
CANCER EPIDEMIOLOGY BIOMARKERS & PREVENTION
(2023)
Meeting Abstract
Oncology
Janet H. Van Cleave, Catherine Concert, Kenneth S. Hu, Eva Liang, Brian L. Egleston
ONCOLOGY NURSING FORUM
(2022)