Article
Statistics & Probability
Jingfei Zhang, Yi Li
Summary: This article proposes a Gaussian graphical regression model to link graph structures to external covariates. In co-expression QTL studies, the method can determine how genetic variants and clinical conditions modulate network structures, and recover gene networks. The utility and efficacy of the method is demonstrated through simulation studies and an application example.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Economics
Alexander D'Amour, Peng Ding, Avi Feller, Lihua Lei, Jasjeet Sekhon
Summary: This paper discusses the key assumptions for estimating causal effects under exogeneity, including unconfoundedness and overlap. Researchers often argue that unconfoundedness is more plausible when more covariates are included in the analysis, while less discussed is the difficulty of satisfying covariate overlap. By exploiting results from information theory, the authors derive explicit bounds on the average imbalance in covariate means under strict overlap, showing that these bounds become more restrictive as the dimension grows large.
JOURNAL OF ECONOMETRICS
(2021)
Article
Biochemical Research Methods
Qian Gao, Yu Zhang, Hongwei Sun, Tong Wang
Summary: This paper reviews the methods for estimating causal effects in observational studies and evaluates their performance in high-dimensional settings. The simulation experiments show that GLiDeR and hdCBPS approaches perform well in terms of estimation accuracy, but further studies are needed for constructing valid confidence intervals.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Gianna Serafina Monti, Peter Filzmoser
Summary: High-throughput sequencing technologies provide a large amount of data for microbiome composition analysis, which requires consideration of data sparsity and uniqueness. This article proposes a regression variable selection method that takes into account the special nature of microbiome data, achieving sparsity and robustness in regression coefficient estimates through elastic-net regularization. The practical utility of the method is demonstrated through real-world application and simulation studies.
Article
Statistics & Probability
Wei Qian, Ching-Kang Ing, Ji Liu
Summary: This article explores a significant sequential decision making problem, which is the multi-armed stochastic bandit problem with covariates. Under the linear bandit framework with high-dimensional covariates, a general multi-stage arm allocation algorithm is proposed, which integrates arm elimination and randomized assignment strategies. By employing high-dimensional regression methods for coefficient estimation, the algorithm achieves near optimal finite-time regret performance under a new study scope.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Economics
Qinqin Hu, Lu Lin
Summary: A new feature screening tool and a two-stage regularization framework were proposed to tackle high dimensionality and endogeneity issues, demonstrating consistency in ranking with exponential growth of predictors. Simulation studies supported the effectiveness of the proposed method.
COMPUTATIONAL ECONOMICS
(2022)
Article
Mathematics
Zeyu Diao, Lili Yue, Fanrong Zhao, Gaorong Li
Summary: This paper proposes a novel method for estimating ATE by combining SPAC and regression adjustment methods. The proposed SPAC adjustment method shows better performance than traditional high-dimensional regression adjustment methods when the covariates are highly correlated.
Article
Genetics & Heredity
Zhangsheng Yu, Yidan Cui, Ting Wei, Yanran Ma, Chengwen Luo
Summary: Mediation analysis is a statistical method used to investigate the mechanism of environmental exposures on health outcomes. Researchers propose a high-dimensional mediation analysis procedure using propensity score for adjustment to account for potential confounders. Simulation studies show that this procedure performs well in mediator selection and effect estimation, even as sample size increases.
FRONTIERS IN GENETICS
(2021)
Article
Statistics & Probability
Yumou Qiu, Jing Tao, Xiao-Hua Zhou
Summary: This study introduces a novel approach for estimating and inferring heterogeneous local treatment effects using high-dimensional covariates and observational data without strong assumptions. By identifying parameters of interest with a binary instrumental variable, it develops Lasso estimation and debiased estimator methods for constructing confidence intervals for treatment effects conditioned on covariates, correcting biases caused by high-dimensional estimation at both stages. Performance is evaluated through simulation studies and real data analysis on the Oregon Health Insurance Experiment.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
(2021)
Article
Economics
Alexander Kreiss, C. Rothe
Summary: We study regression discontinuity designs and propose a two-step estimator to increase the precision of treatment effect estimates by including many predetermined covariates. The estimator first selects important covariates through a localised lasso-type procedure and then estimates the treatment effect using a local linear estimator. The algorithm's theoretical properties are analyzed, showing that the resulting estimator is asymptotically normal under certain conditions.
ECONOMETRICS JOURNAL
(2023)
Article
Economics
Dongxiao Han, Jian Huang, Yuanyuan Lin, Lei Liu, Lianqiang Qu, Liuquan Sun
Summary: This article proposes a robust signal recovery method for high-dimensional linear log-contrast models, capable of handling heavy-tailed and asymmetric error distributions. The method is based on Huber loss with l(1) penalization, and its effectiveness is evaluated through simulation studies and applied to GDP satisfaction and HIV microbiome datasets.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Statistics & Probability
Caroline Svahn, Oleg Sysoev
Summary: Efficient modeling of censored data is crucial for various applications. This article presents a selective multiple imputation approach for predictive modeling in the presence of high-dimensional censored data. The proposed method allows for iterative selection of covariates to impute, resulting in a fast and accurate predictive model. Compared to previous methods, this fully nonparametric approach is more flexible and achieves comparable accuracy with faster execution.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2022)
Article
Health Care Sciences & Services
Anthony Devaux, Catherine Helmer, Robin Genuer, Cecile Proust-Lima
Summary: Predicting the individual risk of clinical events using the complete patient history is challenging. This study extends the competing-risk random survival forests method to handle endogenous longitudinal predictors and compute individual event probabilities. The method transforms predictors into fixed features and computes the final event probability using estimators from multiple trees. The study compares the performance of this method to alternative approaches and demonstrates its usefulness in dementia research.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2023)
Article
Statistics & Probability
Chris McKennan, Dan Nicolae
Summary: This article presents two methods, CBCV and CorrConf, for handling high-dimensional biological datasets with complex sample correlation structures. These methods demonstrate superior performance in choosing the number of latent confounding factors and estimating them, as evidenced by analysis of simulated and real data applications.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Statistics & Probability
Runze Li, Kai Xu, Yeqing Zhou, Liping Zhu
Summary: In this article, we propose a novel test based on an aggregation of the marginal cumulative covariances to accommodate heteroscedasticity and high dimensionality in high-dimensional data. Our proposed test statistic is scale-invariance, tuning-free, and easy to implement, with established asymptotic normality under the null hypothesis. We find that our proposed test is much more powerful than existing competitors for covariates with heterogeneous variances, even under high-dimensional linear models, while maintaining high efficiency for homoscedastic covariates.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
