scholarly journals Sensitivity Analysis in Nonrandomized Longitudinal Mediation Analysis

2021 ◽  
Vol 12 ◽  
Author(s):  
Davood Tofighi
Keyword(s):  
Sensitivity Analysis ◽  
Mediation Analysis ◽  
Repeated Measures ◽  
Outcome Variable ◽  
Latent Growth ◽  
Confounding Bias ◽  
Analysis Technique ◽  
Slope Modeling ◽  
Antecedent Variable ◽  
Addiction Studies

Mediation analysis relies on an untestable assumption of the no omitted confounders, which posits that an omitted variable that confounds the relationships between the antecedent, mediator, and outcome variables cannot exist. One common model in alcohol addiction studies is a nonrandomized latent growth curve mediation model (LGCMM), where the antecedent variable is not randomized, the two covarying mediators are latent intercept and slope modeling longitudinal effect of the repeated measures mediator, and an outcome variable that measures alcohol use. An important gap in the literature is lack of sensitivity analysis techniques to assess the effect of the violation of the no omitted confounder assumption in a nonrandomized LGCMM. We extend a sensitivity analysis technique, termed correlated augmented mediation sensitivity analysis (CAMSA), to a nonrandomized LGCMM. We address several unresolved issues in conducting CAMSA for the nonrandomized LGCMM and present: (a) analytical results showing how confounder correlations model a confounding bias, (b) algorithms to address admissible values for confounder correlations, (c) accessible R code within an SEM framework to conduct our proposed sensitivity analysis, and (d) an empirical example. We conclude that conducting sensitivity analysis to ascertain robustness of the mediation analysis is critical.

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 Conditional Process Analysis in Two-Instance Repeated-Measures Designs

2019 ◽  
Author(s):  
Amanda Kay Montoya
Keyword(s):  
Mediation Analysis ◽  
Repeated Measures ◽  
Process Analysis ◽  
Repeated Measurements ◽  
Process Models ◽  
Outcome Variable ◽  
Moderation Analysis ◽  
Repeated Measures Design ◽  
Independent Variable ◽  
Conditional Process Analysis

Conditional process models are commonly used in many areas of psychology research as well as research in other academic fi?elds (e.g., marketing, communication, and education). Conditional process models combine mediation analysis and moderation analysis. Mediation analysis, sometimes called process analysis, investigates if an independent variable influences an outcome variable through a specific?c intermediary variable, sometimes called a mediator. Moderation analysis investigates if the relationship between two variables depends on another. Conditional process models are very popular because they allow us to better understand how the processes we are interested in might vary depending on characteristics of different individuals, situations, and other moderating variables. Methodological developments in conditional process analysis have primarily focused on the analysis of data collected using between-subjects experimental designs or cross-sectional designs. However, another very common design is the two-instance repeated-measures design. A two-instance repeated-measures design is one where each subject is measured twice; once in each of two instances. In the analysis discussed in this dissertation, the factor that differentiates the two repeated measurements is the independent variable of interest. Research on how to statistically test mediation, moderation, and conditional process models in these designs has been minimal. Judd, Kenny, and McClelland (2001) introduced a piece-wise method for testing for mediation, reminiscent of the Baron and Kenny causal steps approach for between-participant designs. Montoya and Hayes (2017) took thispiece-wise approach and translated it to a path-analytic approach, allowing for a quanti?cation of the indirect e?ect, more sophisticated methods of inference, and the extension to multiple mediator models. Moderation analysis in these designs has been described by Judd, McClelland, and Smith (1996), Judd et al. (2001), and Montoya (in press). However, the generalization to conditional process analysis, or moderated mediation, remains unknown. Describing this approach is the purpose of this dissertation.

scholarly journals Sensitivity analysis for unobserved confounding in causal mediation analysis allowing for effect modification, censoring and truncation

2021 ◽  
Author(s):  
Anita Lindmark
Keyword(s):  
Sensitivity Analysis ◽  
Mediation Analysis ◽  
Regression Models ◽  
Effect Modification ◽  
Outcome Variable ◽  
Parametric Regression ◽  
Intermediate Variable ◽  
Causal Mediation ◽  
Causal Mediation Analysis ◽  
Parametric Regression Models

AbstractCausal mediation analysis is used to decompose the total effect of an exposure on an outcome into an indirect effect, taking the path through an intermediate variable, and a direct effect. To estimate these effects, strong assumptions are made about unconfoundedness of the relationships between the exposure, mediator and outcome. These assumptions are difficult to verify in a given situation and therefore a mediation analysis should be complemented with a sensitivity analysis to assess the possible impact of violations. In this paper we present a method for sensitivity analysis to not only unobserved mediator-outcome confounding, which has largely been the focus of previous literature, but also unobserved confounding involving the exposure. The setting is estimation of natural direct and indirect effects based on parametric regression models. We present results for combinations of binary and continuous mediators and outcomes and extend the sensitivity analysis for mediator-outcome confounding to cases where the continuous outcome variable is censored or truncated. The proposed methods perform well also in the presence of interactions between the exposure, mediator and observed confounders, allowing for modeling flexibility as well as exploration of effect modification. The performance of the method is illustrated through simulations and an empirical example.

scholarly journals Serum syndecan-1 reflects organ dysfunction in critically ill patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Keiko Suzuki ◽  
Hideshi Okada ◽  
Kazuyuki Sumi ◽  
Hiroyuki Tomita ◽  
Ryo Kobayashi ◽  
...  
Keyword(s):  
Risk Factor ◽  
Critically Ill ◽  
Organ Dysfunction ◽  
Critically Ill Patients ◽  
Repeated Measures ◽  
Significant Risk ◽  
Mixed Effects ◽  
Mixed Effects Models ◽  
Endothelial Glycocalyx ◽  
Outcome Variable

AbstractSyndecan-1 (SDC-1) is found in the endothelial glycocalyx and shed into the blood during systemic inflammatory conditions. We investigated organ dysfunction associated with changing serum SDC-1 levels for early detection of organ dysfunction in critically ill patients. To evaluate the effect of SDC-1 on laboratory parameters measured the day after SDC-1 measurement with consideration for repeated measures, linear mixed effects models were constructed with each parameter as an outcome variable. A total of 94 patients were enrolled, and 831 samples were obtained. Analysis using mixed effects models for repeated measures with adjustment for age and sex showed that serum SDC-1 levels measured the day before significantly affected several outcomes, including aspartate aminotransferase (AST), alanine transaminase (ALT), creatinine (CRE), blood urea nitrogen (BUN), antithrombin III, fibrin degradation products, and D-dimer. Moreover, serum SDC-1 levels of the prior day significantly modified the effect between time and several outcomes, including AST, ALT, CRE, and BUN. Additionally, increasing serum SDC-1 level was a significant risk factor for mortality. Serum SDC-1 may be a useful biomarker for daily monitoring to detect early signs of kidney, liver and coagulation system dysfunction, and may be an important risk factor for mortality in critically ill patients.

scholarly journals Multi-Objective Robust Optimization Using a Postoptimality Sensitivity Analysis Technique: Application to a Wind Turbine Design

2015 ◽  
Vol 137 (1) ◽  
Author(s):  
Weijun Wang ◽  
Stéphane Caro ◽  
Fouad Bennis ◽  
Ricardo Soto ◽  
Broderick Crawford
Keyword(s):  
Sensitivity Analysis ◽  
Robust Optimization ◽  
Wind Turbine ◽  
Optimization Design ◽  
Optimization Problems ◽  
Design Environment ◽  
Multi Objective ◽  
Pareto Ranking ◽  
Analysis Technique ◽  
Robust Optimization Design

Toward a multi-objective optimization robust problem, the variations in design variables (DVs) and design environment parameters (DEPs) include the small variations and the large variations. The former have small effect on the performance functions and/or the constraints, and the latter refer to the ones that have large effect on the performance functions and/or the constraints. The robustness of performance functions is discussed in this paper. A postoptimality sensitivity analysis technique for multi-objective robust optimization problems (MOROPs) is discussed, and two robustness indices (RIs) are introduced. The first one considers the robustness of the performance functions to small variations in the DVs and the DEPs. The second RI characterizes the robustness of the performance functions to large variations in the DEPs. It is based on the ability of a solution to maintain a good Pareto ranking for different DEPs due to large variations. The robustness of the solutions is treated as vectors in the robustness function space (RF-Space), which is defined by the two proposed RIs. As a result, the designer can compare the robustness of all Pareto optimal solutions and make a decision. Finally, two illustrative examples are given to highlight the contributions of this paper. The first example is about a numerical problem, whereas the second problem deals with the multi-objective robust optimization design of a floating wind turbine.

scholarly journals Mathematical Modeling of Public Opinions: Parameter Estimation, Sensitivity Analysis, and Model Uncertainty Using an Agree-Disagree Opinion Model

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Sara Bidah ◽  
Omar Zakary ◽  
Mostafa Rachik ◽  
Hanane Ferjouchia
Keyword(s):  
Sensitivity Analysis ◽  
Control Strategies ◽  
Nonlinear Least Squares ◽  
Real Data ◽  
Outcome Variable ◽  
Polling System ◽  
Least Squares Regression ◽  
Approval Rating ◽  
Statistical Experiments ◽  
The Stability

In this paper, we present a mathematical model that describes agree-disagree opinions during polls. We first present the different compartments of the model. Then, using the next-generation matrix method, we derive thresholds of the stability of equilibria. We consider two sets of data from the Reuters polling system regarding the approval rating of the U.S presidential in two terms. These two weekly polls data track the percentage of Americans who approve and disapprove of the way the President manages his work. To validate the reality of the underlying model, we use nonlinear least-squares regression to fit the model to actual data. In the first poll, we consider only 31 weeks to estimate the parameters of the model, and then, we compare the rest of the data with the outcome of the model over the remaining 21 weeks. We show that our model fits correctly the real data. The second poll data is collected for 115 weeks. We estimate again the parameters of the model, and we show that our model can predict the poll outcome in the next weeks, thus, whether the need for some control strategies or not. Finally, we also perform several computational and statistical experiments to validate the proposed model in this paper. To study the influence of various parameters on these thresholds and to identify the most influential parameters, sensitivity analysis is carried out to investigate the effect of the small perturbation near a parameter value on the value of the threshold. An uncertainty analysis is performed to evaluate the forecast inaccuracy in the outcome variable due to uncertainty in the estimation of the parameters.

Sign in / Sign up

Export Citation Format

Share Document