Zhi Geng
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
Zhi Geng has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Fuzhong Xue
Department of Medical Dataology, School of Public Health, Cheeloo College of Medicine, Shandong University, China
4 shared publications - Hongkai Li
Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, China
4 shared publications - Xueli Wang
School of Mathematics and Statistics, Beijing Technology and Business University, Beijing 102488, China
4 shared publications - Jinzhu Jia
Department of Biostatistics, School of Public Health, Peking University, Beijing, China
3 shared publications - Wang Miao
Department of Probability and Statistics, Peking University
3 shared publications - Wei Li
Center for Applied Statistics and School of Statistics, Renmin University of China
3 shared publications
Latest Publications
- 20 June 2025
- Published by Springer Nature
- p. 2748-2750
Surrogate Paradox
- Open Access
- 1 January 2025
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 19 (2) , 3723-3742
Efficiency-improved doubly robust estimation with non-confounding predictive covariates
The doubly robust (DR) estimators are widely utilized in observational studies to estimate the average treatment effect due to their consistency when either the outcome model or propensity score is correctly specified. However, in practice, the DR estimator may exhibit significant estimation variability due to misspecification of the outcome model. This paper introduces an alternative DR estimator to enhance efficiency when the outcome model may be misspecified. Specifically, our estimator achieves the smallest asymptotic variance among all DR estimators when the propensity score model is correctly specified, while retaining the double robustness property. To further improve efficiency, we incorporate additional covariates that have predictive power for the outcome variable but do not affect the treatment variable. Simulation studies demonstrate the superior performance of our proposed estimator compared to existing methods. Additionally, we provide two real data analyses to illustrate the proposed method.
- 1 January 2025
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 19 (2) , 3723-3742
Open AccessEfficiency-improved doubly robust estimation with non-confounding predictive covariates
The doubly robust (DR) estimators are widely utilized in observational studies to estimate the average treatment effect due to their consistency when either the outcome model or propensity score is correctly specified. However, in practice, the DR estimator may exhibit significant estimation variability due to misspecification of the outcome model. This paper introduces an alternative DR estimator to enhance efficiency when the outcome model may be misspecified. Specifically, our estimator achieves the smallest asymptotic variance among all DR estimators when the propensity score model is correctly specified, while retaining the double robustness property. To further improve efficiency, we incorporate additional covariates that have predictive power for the outcome variable but do not affect the treatment variable. Simulation studies demonstrate the superior performance of our proposed estimator compared to existing methods. Additionally, we provide two real data analyses to illustrate the proposed method.
- Open Access
- 10 September 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (18) , 2801
Identifiability and Estimation for Potential-Outcome Means with Misclassified Outcomes
Potential outcomes play a fundamental and important role in many causal inference problems. If the potential-outcome means are identifiable, a series of causal effect measures, including the risk difference, the risk ratio, and the treatment benefit rate, among others, can also be identified. However, current identification and estimation methods for these means often implicitly assume that the collected data for analysis are measured precisely. In many fields such as medicine and economics, the collected variables may be subject to measurement errors, such as medical diagnostic results and individual wage data. Misclassification, as a non-classic measurement error, can lead to severely biased estimates in causal inference. In this paper, we leverage a combined sample to study the identifiability of potential-outcome means corresponding to different treatment levers under a plausible misclassification assumption for the outcome, allowing the misclassification probability to depend on not only the true outcome but also the covariates. Furthermore, we propose the multiply-robust and semiparametric efficient estimators for the means, consistent even under partial misspecification of the observed data law, based on the semiparametric theory framework. The simulation studies and real data analysis demonstrate the satisfactory performance of the proposed method.
- 10 September 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (18) , 2801
Open AccessIdentifiability and Estimation for Potential-Outcome Means with Misclassified Outcomes
Potential outcomes play a fundamental and important role in many causal inference problems. If the potential-outcome means are identifiable, a series of causal effect measures, including the risk difference, the risk ratio, and the treatment benefit rate, among others, can also be identified. However, current identification and estimation methods for these means often implicitly assume that the collected data for analysis are measured precisely. In many fields such as medicine and economics, the collected variables may be subject to measurement errors, such as medical diagnostic results and individual wage data. Misclassification, as a non-classic measurement error, can lead to severely biased estimates in causal inference. In this paper, we leverage a combined sample to study the identifiability of potential-outcome means corresponding to different treatment levers under a plausible misclassification assumption for the outcome, allowing the misclassification probability to depend on not only the true outcome but also the covariates. Furthermore, we propose the multiply-robust and semiparametric efficient estimators for the means, consistent even under partial misspecification of the observed data law, based on the semiparametric theory framework. The simulation studies and real data analysis demonstrate the satisfactory performance of the proposed method.
- Open Access
- 22 January 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (2)
MRSL: a causal network pruning algorithm based on GWAS summary data
Causal discovery is a powerful tool to disclose underlying structures by analyzing purely observational data. Genetic variants can provide useful complementary information for structure learning. Recently, Mendelian randomization (MR) studies have provided abundant marginal causal relationships of traits. Here, we propose a causal network pruning algorithm MRSL (MR-based structure learning algorithm) based on these marginal causal relationships. MRSL combines the graph theory with multivariable MR to learn the conditional causal structure using only genome-wide association analyses (GWAS) summary statistics. Specifically, MRSL utilizes topological sorting to improve the precision of structure learning. It proposes MR-separation instead of d-separation and three candidates of sufficient separating set for MR-separation. The results of simulations revealed that MRSL had up to 2-fold higher F1 score and 100 times faster computing time than other eight competitive methods. Furthermore, we applied MRSL to 26 biomarkers and 44 International Classification of Diseases 10 (ICD10)-defined diseases using GWAS summary data from UK Biobank. The results cover most of the expected causal links that have biological interpretations and several new links supported by clinical case reports or previous observational literatures.
- 22 January 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (2)
Open AccessMRSL: a causal network pruning algorithm based on GWAS summary data
Causal discovery is a powerful tool to disclose underlying structures by analyzing purely observational data. Genetic variants can provide useful complementary information for structure learning. Recently, Mendelian randomization (MR) studies have provided abundant marginal causal relationships of traits. Here, we propose a causal network pruning algorithm MRSL (MR-based structure learning algorithm) based on these marginal causal relationships. MRSL combines the graph theory with multivariable MR to learn the conditional causal structure using only genome-wide association analyses (GWAS) summary statistics. Specifically, MRSL utilizes topological sorting to improve the precision of structure learning. It proposes MR-separation instead of d-separation and three candidates of sufficient separating set for MR-separation. The results of simulations revealed that MRSL had up to 2-fold higher F1 score and 100 times faster computing time than other eight competitive methods. Furthermore, we applied MRSL to 26 biomarkers and 44 International Classification of Diseases 10 (ICD10)-defined diseases using GWAS summary data from UK Biobank. The results cover most of the expected causal links that have biological interpretations and several new links supported by clinical case reports or previous observational literatures.
- Open Access
- 1 January 2024
- Published by Walter de Gruyter GmbH in Journal of Causal Inference
- Vol. 12 (1)
Prospective and retrospective causal inferences based on the potential outcome framework
In this article, we discuss both prospective and retrospective causal inferences, building on Neyman’s potential outcome framework. For prospective causal inference, we review criteria for confounders and surrogates to avoid the Yule–Simpson paradox and the surrogate paradox, respectively. For retrospective causal inference, we introduce the concepts of posterior causal effects given observed evidence to quantify the causes of effects. The posterior causal effects provide a unified framework for deducing both effects of causes in prospective causal inference and causes of effects in retrospective causal inference. We compare the medical diagnostic approaches based on Bayesian posterior probabilities and posterior causal effects for classification and attribution.
- 1 January 2024
- Published by Walter de Gruyter GmbH in Journal of Causal Inference
- Vol. 12 (1)
Open AccessProspective and retrospective causal inferences based on the potential outcome framework
In this article, we discuss both prospective and retrospective causal inferences, building on Neyman’s potential outcome framework. For prospective causal inference, we review criteria for confounders and surrogates to avoid the Yule–Simpson paradox and the surrogate paradox, respectively. For retrospective causal inference, we introduce the concepts of posterior causal effects given observed evidence to quantify the causes of effects. The posterior causal effects provide a unified framework for deducing both effects of causes in prospective causal inference and causes of effects in retrospective causal inference. We compare the medical diagnostic approaches based on Bayesian posterior probabilities and posterior causal effects for classification and attribution.
- 2 November 2021
- Published by Wiley in Statistics in Medicine
- Vol. 41 (2) , 328-339
A causal data fusion method for the general exposure and outcome
With the advent of the big data era, the need to combine multiple individual data sets to draw causal effects arises naturally in many medical and biological applications. Especially each data set cannot measure enough confounders to infer the causal effect of an exposure on an outcome. In this article, we extend the method proposed by a previous study to causal data fusion of more than two data sets without external validation and to a more general (continuous or discrete) exposure and outcome. Theoretically, we obtain the condition for identifiability of exposure effects using multiple individual data sources for the continuous or discrete exposure and outcome. The simulation results show that our proposed causal data fusion method has unbiased causal effect estimate and higher precision than traditional regression, meta-analysis and statistical matching methods. We further apply our method to study the causal effect of BMI on glucose level in individuals with diabetes by combining two data sets. Our method is essential for causal data fusion and provides important insights into the ongoing discourse on the empirical analysis of merging multiple individual data sources.
- 2 November 2021
- Published by Wiley in Statistics in Medicine
- Vol. 41 (2) , 328-339
A causal data fusion method for the general exposure and outcome
With the advent of the big data era, the need to combine multiple individual data sets to draw causal effects arises naturally in many medical and biological applications. Especially each data set cannot measure enough confounders to infer the causal effect of an exposure on an outcome. In this article, we extend the method proposed by a previous study to causal data fusion of more than two data sets without external validation and to a more general (continuous or discrete) exposure and outcome. Theoretically, we obtain the condition for identifiability of exposure effects using multiple individual data sources for the continuous or discrete exposure and outcome. The simulation results show that our proposed causal data fusion method has unbiased causal effect estimate and higher precision than traditional regression, meta-analysis and statistical matching methods. We further apply our method to study the causal effect of BMI on glucose level in individuals with diabetes by combining two data sets. Our method is essential for causal data fusion and provides important insights into the ongoing discourse on the empirical analysis of merging multiple individual data sources.
- 26 April 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (17) , 3975-3989
Causal mediation analysis with sure outcomes of random events model
Mediation analysis is a useful tool in randomized trials for understanding how a treatment works, in particular how much of the treatment's effect on an outcome is explained by a mediator variable. The traditional approach to mediation analysis makes sequential ignorability assumption which precludes the existence of unobserved confounders between the mediator and outcome variables. Since the randomized experiment does not randomize the mediator, sequential ignorability may not be plausible. In this article, based on a statistical model termed sure outcomes of random events model, we propose an alternative approach to causal mediation analysis without relying on the sequential ignorability assumption for the case of binary treatment and mediator variables. When the outcome is also binary, we establish the identifiability of the average natural direct and indirect effects in the presence of an unobserved confounder between mediator and outcome variables. More importantly, if the identifiability conditions are violated, we provide new bounds that are narrower than those in the previous studies, and these bound results are extended to the case of an arbitrary bounded outcome. Simulation studies show good performance for the proposed estimators in finite samples. Finally, we use a job training intervention on the mental health study to illustrate our approach.
- 26 April 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (17) , 3975-3989
Causal mediation analysis with sure outcomes of random events model
Mediation analysis is a useful tool in randomized trials for understanding how a treatment works, in particular how much of the treatment's effect on an outcome is explained by a mediator variable. The traditional approach to mediation analysis makes sequential ignorability assumption which precludes the existence of unobserved confounders between the mediator and outcome variables. Since the randomized experiment does not randomize the mediator, sequential ignorability may not be plausible. In this article, based on a statistical model termed sure outcomes of random events model, we propose an alternative approach to causal mediation analysis without relying on the sequential ignorability assumption for the case of binary treatment and mediator variables. When the outcome is also binary, we establish the identifiability of the average natural direct and indirect effects in the presence of an unobserved confounder between mediator and outcome variables. More importantly, if the identifiability conditions are violated, we provide new bounds that are narrower than those in the previous studies, and these bound results are extended to the case of an arbitrary bounded outcome. Simulation studies show good performance for the proposed estimators in finite samples. Finally, we use a job training intervention on the mental health study to illustrate our approach.
- Open Access
- 8 August 2020
- Published by Springer Nature in BMC Genetics
- Vol. 21 (1) , 1-12
A novel path-specific effect statistic for identifying the differential specific paths in systems epidemiology
Background: Biological pathways play an important role in the occurrence, development and recovery of complex diseases, such as cancers, which are multifactorial complex diseases that are generally caused by mutation of multiple genes or dysregulation of pathways. Results: We propose a path-specific effect statistic (PSE) to detect the differential specific paths under two conditions (e.g. case VS. control groups, exposure Vs. nonexposure groups). In observational studies, the path-specific effect can be obtained by separately calculating the average causal effect of each directed edge through adjusting for the parent nodes of nodes in the specific path and multiplying them under each condition. Theoretical proofs and a series of simulations are conducted to validate the path-specific effect statistic. Applications are also performed to evaluate its practical performances. A series of simulation studies show that the Type I error rates of PSE with Permutation tests are more stable at the nominal level 0.05 and can accurately detect the differential specific paths when comparing with other methods. Specifically, the power reveals an increasing trends with the enlargement of path-specific effects and its effect differences under two conditions. Besides, the power of PSE is robust to the variation of parent or child node of the nodes on specific paths. Application to real data of Glioblastoma Multiforme (GBM), we successfully identified 14 positive specific pathways in mTOR pathway contributing to survival time of patients with GBM. All codes for automatic searching specific paths linking two continuous variables and adjusting set as well as PSE statistic can be found in supplementary materials. Conclusion: The proposed PSE statistic can accurately detect the differential specific pathways contributing to complex disease and thus potentially provides new insights and ways to unlock the black box of disease mechanisms.
- 8 August 2020
- Published by Springer Nature in BMC Genetics
- Vol. 21 (1) , 1-12
Open AccessA novel path-specific effect statistic for identifying the differential specific paths in systems epidemiology
Background: Biological pathways play an important role in the occurrence, development and recovery of complex diseases, such as cancers, which are multifactorial complex diseases that are generally caused by mutation of multiple genes or dysregulation of pathways. Results: We propose a path-specific effect statistic (PSE) to detect the differential specific paths under two conditions (e.g. case VS. control groups, exposure Vs. nonexposure groups). In observational studies, the path-specific effect can be obtained by separately calculating the average causal effect of each directed edge through adjusting for the parent nodes of nodes in the specific path and multiplying them under each condition. Theoretical proofs and a series of simulations are conducted to validate the path-specific effect statistic. Applications are also performed to evaluate its practical performances. A series of simulation studies show that the Type I error rates of PSE with Permutation tests are more stable at the nominal level 0.05 and can accurately detect the differential specific paths when comparing with other methods. Specifically, the power reveals an increasing trends with the enlargement of path-specific effects and its effect differences under two conditions. Besides, the power of PSE is robust to the variation of parent or child node of the nodes on specific paths. Application to real data of Glioblastoma Multiforme (GBM), we successfully identified 14 positive specific pathways in mTOR pathway contributing to survival time of patients with GBM. All codes for automatic searching specific paths linking two continuous variables and adjusting set as well as PSE statistic can be found in supplementary materials. Conclusion: The proposed PSE statistic can accurately detect the differential specific pathways contributing to complex disease and thus potentially provides new insights and ways to unlock the black box of disease mechanisms.
- 20 January 2020
- Published by Wiley in Statistics in Medicine
- Vol. 39 (8) , 1054-1067
Causal data fusion methods using summary‐level statistics for a continuous outcome
In many empirical studies, there exist rich individual studies to separately estimate causal effect of the treatment or exposure variable on the outcome variable, but incomplete confounders are adjusted in each study. Suppose we are interested in the causal effect of a treatment or exposure on an outcome variable, and we have available rich datasets that contain different confounders. How to integrate summary‐level statistics from multiple individual datasets to improve causal inference has become a main challenge in data fusion. We propose a novel method in this article to identify the causal effect of a treatment or exposure on the continuous outcome. We show that the causal effect is identifiable and can be estimated by combining summary‐level statistics from multiple datasets containing subsets of confounders and an external dataset only containing complete confounding information. Simulation studies indicate the unbiasedness of causal effect estimate by our method and we apply our method to a study about the effect of body mass index on fasting blood glucose.
- 20 January 2020
- Published by Wiley in Statistics in Medicine
- Vol. 39 (8) , 1054-1067
Causal data fusion methods using summary‐level statistics for a continuous outcome
In many empirical studies, there exist rich individual studies to separately estimate causal effect of the treatment or exposure variable on the outcome variable, but incomplete confounders are adjusted in each study. Suppose we are interested in the causal effect of a treatment or exposure on an outcome variable, and we have available rich datasets that contain different confounders. How to integrate summary‐level statistics from multiple individual datasets to improve causal inference has become a main challenge in data fusion. We propose a novel method in this article to identify the causal effect of a treatment or exposure on the continuous outcome. We show that the causal effect is identifiable and can be estimated by combining summary‐level statistics from multiple datasets containing subsets of confounders and an external dataset only containing complete confounding information. Simulation studies indicate the unbiasedness of causal effect estimate by our method and we apply our method to a study about the effect of body mass index on fasting blood glucose.
- Open Access
Identification, Doubly Robust Estimation, and Semiparametric Efficiency Theory of Nonignorable Missing Data With a Shadow Variable
We consider identification and estimation with an outcome missing not at random (MNAR). We study an identification strategy based on a so-called shadow variable. A shadow variable is assumed to be correlated with the outcome, but independent of the missingness process conditional on the outcome and fully observed covariates. We describe a general condition for nonparametric identification of the full data law under MNAR using a valid shadow variable. Our condition is satisfied by many commonly-used models; moreover, it is imposed on the complete cases, and therefore has testable implications with observed data only. We describe semiparametric estimation methods and evaluate their performance on both simulation data and a real data example. We characterize the semiparametric efficiency bound for the class of regular and asymptotically linear estimators, and derive a closed form for the efficient influence function.
Open AccessIdentification, Doubly Robust Estimation, and Semiparametric Efficiency Theory of Nonignorable Missing Data With a Shadow Variable
We consider identification and estimation with an outcome missing not at random (MNAR). We study an identification strategy based on a so-called shadow variable. A shadow variable is assumed to be correlated with the outcome, but independent of the missingness process conditional on the outcome and fully observed covariates. We describe a general condition for nonparametric identification of the full data law under MNAR using a valid shadow variable. Our condition is satisfied by many commonly-used models; moreover, it is imposed on the complete cases, and therefore has testable implications with observed data only. We describe semiparametric estimation methods and evaluate their performance on both simulation data and a real data example. We characterize the semiparametric efficiency bound for the class of regular and asymptotically linear estimators, and derive a closed form for the efficient influence function.