Causal Inference Using Mediation Analysis or Instrumental Variables - Full Mediation in the Absence of Conditional Independence

2018 ◽  
Author(s):  
Thomas Otter ◽  
Max J. Pachali ◽  
Stefan Mayer ◽  
Jan Landwehr
Keyword(s):  
Causal Inference ◽  
Instrumental Variables ◽  
Mediation Analysis ◽  
Conditional Independence

scholarly journals The Role of Instrumental Variables in Causal Inference Based on Independence of Cause and Mechanism

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 928
Author(s):  
Nataliya Sokolovska ◽  
Pierre-Henri Wuillemin
Keyword(s):  
Causal Inference ◽  
Instrumental Variables ◽  
Latent Variables ◽  
Conditional Independence ◽  
State Of The Art ◽  
Simulated Data ◽  
Research Directions ◽  
Common Causes ◽  
Inference Methods

Causal inference methods based on conditional independence construct Markov equivalent graphs and cannot be applied to bivariate cases. The approaches based on independence of cause and mechanism state, on the contrary, that causal discovery can be inferred for two observations. In our contribution, we pose a challenge to reconcile these two research directions. We study the role of latent variables such as latent instrumental variables and hidden common causes in the causal graphical structures. We show that methods based on the independence of cause and mechanism indirectly contain traces of the existence of the hidden instrumental variables. We derive a novel algorithm to infer causal relationships between two variables, and we validate the proposed method on simulated data and on a benchmark of cause-effect pairs. We illustrate by our experiments that the proposed approach is simple and extremely competitive in terms of empirical accuracy compared to the state-of-the-art methods.

scholarly journals Mendelian randomisation for mediation analysis: current methods and challenges for implementation

2021 ◽  
Author(s):  
Alice R. Carter ◽  
Eleanor Sanderson ◽  
Gemma Hammerton ◽  
Rebecca C. Richmond ◽  
George Davey Smith ◽  
...  
Keyword(s):  
Measurement Error ◽  
Causal Inference ◽  
Mediation Analysis ◽  
Instrumental Variable ◽  
Real Data ◽  
Mendelian Randomisation ◽  
Differential Measurement ◽  
Individual Level ◽  
Differential Measurement Error ◽  
Summary Data

AbstractMediation analysis seeks to explain the pathway(s) through which an exposure affects an outcome. Traditional, non-instrumental variable methods for mediation analysis experience a number of methodological difficulties, including bias due to confounding between an exposure, mediator and outcome and measurement error. Mendelian randomisation (MR) can be used to improve causal inference for mediation analysis. We describe two approaches that can be used for estimating mediation analysis with MR: multivariable MR (MVMR) and two-step MR. We outline the approaches and provide code to demonstrate how they can be used in mediation analysis. We review issues that can affect analyses, including confounding, measurement error, weak instrument bias, interactions between exposures and mediators and analysis of multiple mediators. Description of the methods is supplemented by simulated and real data examples. Although MR relies on large sample sizes and strong assumptions, such as having strong instruments and no horizontally pleiotropic pathways, our simulations demonstrate that these methods are unaffected by confounders of the exposure or mediator and the outcome and non-differential measurement error of the exposure or mediator. Both MVMR and two-step MR can be implemented in both individual-level MR and summary data MR. MR mediation methods require different assumptions to be made, compared with non-instrumental variable mediation methods. Where these assumptions are more plausible, MR can be used to improve causal inference in mediation analysis.

scholarly journals Causal Inference Between Chronic Periodontitis and Chronic Kidney Disease: A Bidirectional Mendelian Randomization Analysis in a European Population

2021 ◽  
Vol 12 ◽  
Author(s):  
Jie Yang ◽  
Tianyi Chen ◽  
Yahong Zhu ◽  
Mingxia Bai ◽  
Xingang Li
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Causal Inference ◽  
Causal Relationship ◽  
Instrumental Variables ◽  
Chronic Periodontitis ◽  
Mendelian Randomization ◽  
Association Studies ◽  
Genome Wide Association Studies ◽  
Summary Statistics

BackgroundPrevious epidemiological studies have shown significant associations between chronic periodontitis (CP) and chronic kidney disease (CKD), but the causal relationship remains uncertain. Aiming to examine the causal relationship between these two diseases, we conducted a bidirectional two-sample Mendelian randomization (MR) analysis with multiple MR methods.MethodsFor the casual effect of CP on CKD, we selected seven single-nucleotide polymorphisms (SNPs) specific to CP as genetic instrumental variables from the genome-wide association studies (GWAS) in the GLIDE Consortium. The summary statistics of complementary kidney function measures, i.e., estimated glomerular filtration rate (eGFR) and blood urea nitrogen (BUN), were derived from the GWAS in the CKDGen Consortium. For the reversed causal inference, six SNPs associated with eGFR and nine with BUN from the CKDGen Consortium were included and the summary statistics were extracted from the CLIDE Consortium.ResultsNo significant causal association between genetically determined CP and eGFR or BUN was found (all p > 0.05). Based on the conventional inverse variance-weighted method, one of seven instrumental variables supported genetically predicted CP being associated with a higher risk of eGFR (estimate = 0.019, 95% CI: 0.012–0.026, p < 0.001).ConclusionEvidence from our bidirectional causal inference does not support a causal relation between CP and CKD risk and therefore suggests that associations reported by previous observational studies may represent confounding.

scholarly journals Mendelian randomisation for mediation analysis: current methods and challenges for implementation

2019 ◽  
Author(s):  
Alice R Carter ◽  
Eleanor Sanderson ◽  
Gemma Hammerton ◽  
Rebecca C Richmond ◽  
George Davey Smith ◽  
...  
Keyword(s):  
Measurement Error ◽  
Causal Inference ◽  
Mediation Analysis ◽  
Real Data ◽  
Mendelian Randomisation ◽  
Reverse Causality ◽  
Differential Measurement ◽  
Individual Level ◽  
Differential Measurement Error ◽  
Summary Data

AbstractMediation analysis seeks to explain the pathway(s) through which an exposure affects an outcome. Mediation analysis experiences a number of methodological difficulties, including bias due to confounding and measurement error. Mendelian randomisation (MR) can be used to improve causal inference for mediation analysis. We describe two approaches that can be used for estimating mediation analysis with MR: multivariable Mendelian randomisation (MVMR) and two-step Mendelian randomisation. We outline the approaches and provide code to demonstrate how they can be used in mediation analysis. We review issues that can affect analyses, including confounding, measurement error, weak instrument bias, and analysis of multiple mediators. Description of the methods is supplemented by simulated and real data examples. Although Mendelian randomisation relies on large sample sizes and strong assumptions, such as having strong instruments and no horizontally pleiotropic pathways, our examples demonstrate that it is unlikely to be affected by confounders of the exposure or mediator and the outcome, reverse causality and non-differential measurement error of the exposure or mediator. Both MVMR and two-step MR can be implemented in both individual-level MR and summary data MR, and can improve causal inference in mediation analysis.

scholarly journals Extended conditional independence and applications in causal inference

2017 ◽  
Vol 45 (6) ◽  
pp. 2618-2653 ◽  
Author(s):  
Panayiota Constantinou ◽  
A. Philip Dawid
Keyword(s):  
Causal Inference ◽  
Conditional Independence
Sign in / Sign up

Export Citation Format

Share Document