Power and instrument strength requirements for Mendelian randomization studies using multiple genetic variants.

By Brandon L. Pierce, H. Ahsan, Tyler J. VanderWeele. International Journal of Epidemiology, 2011

1,625 citations recorded by the source corpus.

Subfields: Genetics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/9d889a56d465f3c1184f907c221bb33d477f99ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

1. Stephen Burgess
2. George Davey Smith
3. J. Bowden
4. S. Thompson
5. Nuala Sheehan
6. Cosetta Minelli
7. E. Sanderson
8. J. Thompson

In Statistics and Probability

1. Stephen Burgess
2. George Davey Smith
3. S. Thompson
4. J. Bowden
5. Cosetta Minelli
6. Nuala Sheehan
7. Adam S. Butterworth
8. J. Thompson

Citations in the corpus

• Causal Relationship between Obesity and Vitamin D Status: Bi-Directional Mendelian Randomization Analysis of Multiple Cohorts (2013, methodology): “However, as shown by the clear outcome of these analyses, we were able to overcome these issues by combining several cohorts with comparable information, allowing us to achieve the large numbers required (maximum n = 42,024) [31].”
• Detecting pleiotropy in Mendelian randomisation studies with summary data and a continuous outcome (2015, background): “However, the use of multiple independent genetic instruments not only increases the power of the MR analysis [10], but it also allows investigation of pleiotropy [6, 12].”
• Mendelian Randomization Analysis With Multiple Genetic Variants Using Summarized Data (2013, background): “If each variant explains additional variation in the risk factor, then a combined causal estimate using all of the variants will have greater precision than the estimate from any of the individual variants [Pierce et al., 2011].”
• Efficient Design for Mendelian Randomization Studies: Subsample and 2-Sample Instrumental Variable Estimators (2013, methodology): “It is well known that traditional “complete-data” IV estimators are biased towards the confounded association and that bias is most severe when the IV is weak (7, 14).”
• Using multiple genetic variants as instrumental variables for modifiable risk factors (2012, background): “recently estimated the power of Mendelian randomisation studies in a range of settings, using both single and multiple genetic instruments.(13) In studies where genetic data are not obtained from GWAS (in which imputation based on LD is typically performed) there are typically some missing observati”
• Avoiding bias from weak instruments in Mendelian randomization studies. (2011, background): “In general, employing fewer degrees of freedom to model the genetic association, that is using parsimonious models, will increase the F statistic and reduce weak instrument bias [25].”