scholarly journals Longitudinal Mediation Analysis with Time-varying Mediators and Exposures, with Application to Survival Outcomes

2017 ◽  
Vol 5 (2) ◽  
Author(s):  
Wenjing Zheng ◽  
Mark van der Laan
Keyword(s):  
Mediation Analysis ◽  
Past History ◽  
Likelihood Estimation ◽  
Right Censoring ◽  
Survival Outcomes ◽  
Time Varying ◽  
Intermediate Variable ◽  
Influence Curves ◽  
Inverse Probability Weighted ◽  
Natural Decomposition

Abstract:1 In this paper, we study the effect of a time-varying exposure mediated by a time-varying intermediate variable. We consider general longitudinal settings, including survival outcomes. At a given time point, the exposure and mediator of interest are influenced by past covariates, mediators and exposures, and affect future covariates, mediators and exposures. Right censoring, if present, occurs in response to past history. To address the challenges in mediation analysis that are unique to these settings, we propose a formulation in terms of random interventions based on conditional distributions for the mediator. This formulation, in particular, allows for well-defined natural direct and indirect effects in the survival setting, and natural decomposition of the standard total effect. Upon establishing identifiability and the corresponding statistical estimands, we derive the efficient influence curves and establish their robustness properties. Applying Targeted Maximum Likelihood Estimation, we use these efficient influence curves to construct multiply robust and efficient estimators. We also present an inverse probability weighted estimator and a nested non-targeted substitution estimator for these parameters.

Bayesian sensitivity analysis for unmeasured confounding in causal mediation analysis

2017 ◽  
Vol 28 (2) ◽  
pp. 515-531 ◽  
Author(s):  
Lawrence C McCandless ◽  
Julian M Somers
Keyword(s):  
Sensitivity Analysis ◽  
Mediation Analysis ◽  
Indirect Effects ◽  
Direct And Indirect Effects ◽  
Unmeasured Confounding ◽  
Intermediate Variable ◽  
Causal Mediation ◽  
Important Concern ◽  
Analysis Technique ◽  
Causal Mediation Analysis

Causal mediation analysis techniques enable investigators to examine whether the effect of the exposure on an outcome is mediated by some intermediate variable. Motivated by a data example from epidemiology, we consider estimation of natural direct and indirect effects on a survival outcome. An important concern is bias from confounders that may be unmeasured. Estimating natural direct and indirect effects requires an elaborate series of assumptions in order to identify the target quantities. The analyst must carefully measure and adjust for important predictors of the exposure, mediator and outcome. Omitting important confounders may bias the results in a way that is difficult to predict. In recent years, several methods have been proposed to explore sensitivity to unmeasured confounding in mediation analysis. However, many of these methods limit complexity by relying on a handful of sensitivity parameters that are difficult to interpret, or alternatively, by assuming that specific patterns of unmeasured confounding are absent. Instead, we propose a simple Bayesian sensitivity analysis technique that is indexed by four bias parameters. Our method has the unique advantage that it is able to simultaneously assess unmeasured confounding in the mediator–outcome, exposure–outcome and exposure–mediator relationships. It is a natural Bayesian extension of the sensitivity analysis methodologies of VanderWeele, which have been widely used in the epidemiology literature. We present simulation findings, and additionally, we illustrate the method in an epidemiological study of mortality rates in criminal offenders from British Columbia.

scholarly journals Maximum Likelihood Estimation of Time-Varying Sparsity Level for Dynamic Sparse Signals

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 136687-136701
Author(s):  
Thiruppathirajan S. ◽  
Lakshmi Narayanan R. ◽  
Sreelal S. ◽  
Manoj B. S.
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Likelihood Estimation ◽  
Sparse Signals ◽  
Time Varying ◽  
Sparsity Level ◽  
Estimation Of Time

Time-Varying Delay Estimation Applied to the Surface Electromyography Signals Using the Parametric Approach

2018 ◽  
Vol 17 (02) ◽  
pp. 1850015 ◽  
Author(s):  
Gia Thien Luu ◽  
Abdelbassit Boualem ◽  
Tran Trung Duy ◽  
Philippe Ravier ◽  
Olivier Butteli
Keyword(s):  
Parametric Method ◽  
Optimization Technique ◽  
Likelihood Estimation ◽  
Model Parameters ◽  
Fiber Direction ◽  
Time Varying ◽  
Time Varying Delay ◽  
Power Spectral ◽  
Changes Over Time ◽  
Varying Delay

Muscle Fiber Conduction Velocity (MFCV) can be calculated from the time delay between the surface electromyographic (sEMG) signals recorded by electrodes aligned with the fiber direction. In order to take into account the non-stationarity during the dynamic contraction (the most daily life situation) of the data, the developed methods have to consider that the MFCV changes over time, which induces time-varying delays and the data is non-stationary (change of Power Spectral Density (PSD)). In this paper, the problem of TVD estimation is considered using a parametric method. First, the polynomial model of TVD has been proposed. Then, the TVD model parameters are estimated by using a maximum likelihood estimation (MLE) strategy solved by a deterministic optimization technique (Newton) and stochastic optimization technique, called simulated annealing (SA). The performance of the two techniques is also compared. We also derive two appropriate Cramer–Rao Lower Bounds (CRLB) for the estimated TVD model parameters and for the TVD waveforms. Monte-Carlo simulation results show that the estimation of both the model parameters and the TVD function is unbiased and that the variance obtained is close to the derived CRBs. A comparison with non-parametric approaches of the TVD estimation is also presented and shows the superiority of the method proposed.

scholarly journals Case Fatality Risk of the First Pandemic Wave of Coronavirus Disease 2019 (COVID-19) in China

2020 ◽  
Author(s):  
Xiaowei Deng ◽  
Juan Yang ◽  
Wei Wang ◽  
Xiling Wang ◽  
Jiaxin Zhou ◽  
...  
Keyword(s):  
Risk Factors ◽  
Influenza Pandemic ◽  
Mainland China ◽  
Case Fatality ◽  
Likelihood Estimation ◽  
H1n1 Influenza ◽  
Right Censoring ◽  
Time To Event ◽  
Fatality Risk ◽  
Case Fatality Risk

Abstract Background To assess the case fatality risk (CFR) of COVID-19 in mainland China, stratified by region and clinical category, and estimate key time-to-event intervals. Methods We collected individual information and aggregated data on COVID-19 cases from publicly available official sources from 29 December 2019 to 17 April 2020. We accounted for right-censoring to estimate the CFR and explored the risk factors for mortality. We fitted Weibull, gamma, and log-normal distributions to time-to-event data using maximum-likelihood estimation. Results We analyzed 82 719 laboratory-confirmed cases reported in mainland China, including 4632 deaths and 77 029 discharges. The estimated CFR was 5.65% (95% confidence interval [CI], 5.50–5.81%) nationally, with the highest estimate in Wuhan (7.71%) and lowest in provinces outside Hubei (0.86%). The fatality risk among critical patients was 3.6 times that of all patients and 0.8–10.3-fold higher than that of mild-to-severe patients. Older age (odds ratio [OR], 1.14 per year; 95% CI, 1.11–1.16) and being male (OR, 1.83; 95% CI, 1.10–3.04) were risk factors for mortality. The times from symptom onset to first healthcare consultation, to laboratory confirmation, and to hospitalization were consistently longer for deceased patients than for those who recovered. Conclusions Our CFR estimates based on laboratory-confirmed cases ascertained in mainland China suggest that COVID-19 is more severe than the 2009 H1N1 influenza pandemic in hospitalized patients, particularly in Wuhan. Our study provides a comprehensive picture of the severity of the first wave of the pandemic in China. Our estimates can help inform models and the global response to COVID-19.

Sign in / Sign up

Export Citation Format

Share Document