Mendelian randomisation with coarsened exposures
Autor: | Jack Bowden, Kate Tilling, Rachael A. Hughes, Matthew J. Tudball, Qingyuan Zhao, Marcus R. Munafò, Amanda Ly, George Davey Smith |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Epidemiology
Computer science Variation (game tree) Measure (mathematics) 03 medical and health sciences symbols.namesake Bias sensitivity analysis Econometrics Humans latent variable modelling Set (psychology) Genetics (clinical) Research Articles 030304 developmental biology 0303 health sciences 030305 genetics & heredity Genetic Variation biomarkers Mendelian Randomization Analysis Latent Variable Modelling Expression (mathematics) Outcome (probability) Phenotype Sensitivity Analysis Mendelian inheritance symbols Schizophrenia Mendelian randomisation analysis Biomarkers Sign (mathematics) Research Article |
Zdroj: | Tudball, M J, Bowden, J, Hughes, R, Ly, A, Munafo, M R, Tilling, K M, Zhao, Q & Davey Smith, G 2021, ' Mendelian randomisation with coarsened exposures ', Genetic Epidemiology, vol. 45, no. 3, pp. 338-350 . https://doi.org/10.1002/gepi.22376 Genetic Epidemiology |
Popis: | A key assumption in Mendelian randomisation is that the relationship between the genetic instruments and the outcome is fully mediated by the exposure, known as the exclusion restriction assumption. However, in epidemiological studies, the exposure is often a coarsened approximation to some latent continuous trait. For example, latent liability to schizophrenia can be thought of as underlying the binary diagnosis measure. Genetically-driven variation in the outcome can exist within categories of the exposure measurement, thus violating this assumption. We propose a framework to clarify this violation, deriving a simple expression for the resulting bias and showing that it may inflate or deflate effect estimatesbut will not reverse their sign. We then characterise a set of assumptions and a straight-forward method for estimating the effect of standard deviation increases in the latent exposure. Our method relies on a sensitivity parameter which can be interpreted as the genetic variance of the latent exposure. We show that this method can be applied in both the one-sample and two-sample settings. We conclude by demonstrating our method in an applied example and re-analysing two papers which are likely to suffer from this type of bias, allowing meaningful interpretation of their effect sizes. |
Databáze: | OpenAIRE |
Externí odkaz: |