Non-parametric methods with bounds of causal effect

A non-parametric method that estimates upper and lower bounds for an MR causal effect. The bounds are not the same as confidence intervals they reflect the upper and lower limits of an estimated distribution of causal effects. 

Genetic variants must satisfy the IV assumptions. It does not require any of the additional IV assumptions. This method can only be used in the situation of binary (or categorical with few levels) risk factor, IV and outcome. A method for implementing these in Stata has been developed. 

References

• Balke A, Pearl J. Bounds on Treatment Effects from Studies with Imperfect Compliance. Journal of the American Statistical Association 1997;92:1171-1176.
• Palmer TM, Ramsahai RR, Didelez V, Sheehan NA. Nonparametric bounds for the causal effect in a binary instrumental-variable model. Stata Journal 2011;11:345-367.

Other terms in 'One-sample MR methods':

• Generalized Method of Moments (GMM) estimator
• MR with a time-to-event outcome
• Polygenic risk score approach
• Semi-parametric structural mean model (SMMs) for binary outcomes
• TSLS with binary outcome
• Two-stage least squares (TSLS)