Adjusting for bias and unmeasured confounding in Mendelian randomization studies with binary responses.

@article{Palmer2008AdjustingFB,
  title={Adjusting for bias and unmeasured confounding in Mendelian randomization studies with binary responses.},
  author={Tom M Palmer and John R. Thompson and Martin D. Tobin and Nuala A. Sheehan and Paul R. Burton},
  journal={International journal of epidemiology},
  year={2008},
  volume={37 5},
  pages={
          1161-8
        }
}
BACKGROUND Mendelian randomization uses a carefully selected gene as an instrumental-variable (IV) to test or estimate an association between a phenotype and a disease. Classical IV analysis assumes linear relationships between the variables, but disease status is often binary and modelled by a logistic regression. When the linearity assumption between the variables does not hold the IV estimates will be biased. The extent of this bias in the phenotype-disease log odds ratio of a Mendelian… 
View on PubMed
academic.oup.com
81 Citations
Highly Influential Citations
6
Background Citations
19
Methods Citations
17
Results Citations
1

81 Citations

Citation Type

Citation Type

Severity of bias of a simple estimator of the causal odds ratio in Mendelian randomization studies.
TLDR
For a simple data-generating model, the Wald estimator is asymptotically biased with a bias of around 10% in fairly typical Mendelian randomization scenarios but which can be larger in more extreme situations.
Mendelian randomization studies for a continuous exposure under case-control sampling.
TLDR
The results suggest that the naïve estimator is substantially biased under the alternative, yet it remains unbiased under the null hypothesis of no causal effect; the maximum likelihood estimator yields smaller variance and mean squared error than other estimators; and the structural mean models estimator delivers the smallest bias.
Mendelian randomization analysis of case-control data using structural mean models.
TLDR
This paper proposes consistent estimators of the causal relative risk and odds ratio if a priori knowledge is available regarding either the population disease prevalence or the population distribution of the IV (e.g. population allele frequencies), and shows that if no such information is available, approximate estimators can be obtained under a rare disease assumption.
Mendelian randomization using semiparametric linear transformation models.
TLDR
The MR analysis of a lung cancer study suggests a harmful prognostic effect of smoking pack-years that would have been missed by the crude association, and proposes an IV analysis method in the survival context, estimating causal effects on a transformation time and survival probabilities using semiparametric linear transformation models.
The effect of non-differential measurement error on bias, precision and power in Mendelian randomization studies.
TLDR
Understanding the potential effects of measurement error is an important consideration when interpreting estimates from MR analyses and future MR studies should consider methods for accounting for such error and minimizing its impact on inferences derived fromMR analyses.
Instrumental variable estimation of causal risk ratios and causal odds ratios in Mendelian randomization analyses.
TLDR
The authors conclude that point estimates from various IV methods can differ in practical applications, and suggest that structural mean models make weaker assumptions than other IV estimators and can therefore be expected to be consistent in a wider range of situations.
Mendelian Randomization as an Approach to Assess Causality Using Observational Data.
TLDR
Special issues in nephrology are discussed, such as inverse risk factor associations in advanced disease, and opportunities to design Mendelian randomization studies around kidney function and disease are outlined.
Power and instrument strength requirements for Mendelian randomization studies using multiple genetic variants.
TLDR
The feasibility of well-powered, unbiased MR studies will depend upon the amount of variance in the exposure that can be explained by known genetic factors and the 'strength' of the IV set derived from these genetic factors.
A review of instrumental variable estimators for Mendelian randomization
TLDR
Settings particularly relevant to Mendelian randomization are prioritized in the paper, notably the scenario of a continuous exposure and a continuous or binary outcome.
Mendelian Randomization.
TLDR
This chapter provides a step-by-step guide for causal inference based on the principles of MR with a real dataset using both individual and summary data from unrelated individuals to suggest best possible practices and give recommendations based upon the current literature.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Mendelian randomization as an instrumental variable approach to causal inference
TLDR
This framework allows us to address limitations of the Mendelian randomization technique that have often been overlooked in the medical literature and suggests using directed acyclic graphs to check model assumptions by visual inspection.
Mendelian randomization: using genes as instruments for making causal inferences in epidemiology.
TLDR
The use of germline genetic variants that proxy for environmentally modifiable exposures as instruments for these exposures is one form of IV analysis that can be implemented within observational epidemiological studies and can be considered as analogous to randomized controlled trials.
'Mendelian randomization': can genetic epidemiology contribute to understanding environmental determinants of disease?
TLDR
Mendelian randomization provides new opportunities to test causality and demonstrates how investment in the human genome project may contribute to understanding and preventing the adverse effects on human health of modifiable exposures.
Limits to causal inference based on Mendelian randomization: a comparison with randomized controlled trials.
TLDR
The authors conclude that Mendelian randomization is a powerful addition to etiologic research tools, however, care must be taken, because drawing valid causal inferences from its application depends upon more extensive assumptions than are required in randomized controlled trials.
Instrumental Variables: Application and Limitations
TLDR
It is concluded that instrumental variables can be useful in case of moderate confounding but are less useful when strong confounding exists, because strong instruments cannot be found and assumptions will be easily violated.
Estimating treatment effects in randomized clinical trials in the presence of non-compliance.
TLDR
The residual of the regression of the actual treatment indicator variable on the randomization arm indicator variable is shown to 'intercept' the effect of such confounders, and inclusion of this residual in a multivariate analysis, in conjunction with the treatment indicator Variable, should thus adjust for confounding.
Estimation of treatment effects in randomised trials with non-compliance and a dichotomous outcome using structural mean models
We consider estimation of the received treatment effect on a dichotomous outcome in randomised trials with non-compliance. We explore inference about the parameters of the structural mean models of…
Identification of Causal Effects Using Instrumental Variables
TLDR
It is shown that the instrumental variables (IV) estimand can be embedded within the Rubin Causal Model (RCM) and that under some simple and easily interpretable assumptions, the IV estimand is the average causal effect for a subgroup of units, the compliers.
Instruments for Causal Inference: An Epidemiologist's Dream?
TLDR
The definition of an instrumental variable is reviewed, the conditions required to obtain consistent estimates of causal effects are described, and their implications are explored in the context of a recent application of the instrumental variables approach.
Generalized Estimating Equations
Correlated datasets develop when multiple observations are collected from a sampling unit (e.g., repeated measures of a bank over time, or hormone levels in a breast cancer patient over time), or…
...
1
2
3
4
...