Fig. 4From: Genetic insights into the association of statin and newer nonstatin drug target genes with human longevity: a Mendelian randomization analysisFlowchart of the two-step Mendelian randomization for mediation analysis. Two-step Mendelian randomization, where the effect of genetically proxied lipid-lowering target gene variants (Beta A) on the mediator (Major CHD events) and mediator on the human lifespans (Beta B) are estimated separately, using separate genetic instrumental variables for both the exposure and mediator. These estimates are then multiplied together to estimate the indirect effect of the mediator (Beta A*Beta B). Beta C represents the total effect of the exposure to the outcome. The indirect effect (Beta C′) of the exposure to the outcome was estimated using the format: Beta C-Beta A*Beta B. Abbreviations: LDLR, Low-Density Lipoprotein Receptor; CHD, Major coronary heart disease; OR: Odds Ratio; FDR, False discovery rateBack to article page