SISVIVE

Some Invalid Some Valid Instrumental Variable Estimation (SISVIVE). An extension to the TSLS procedure which incorporates LASSO penalization. 

Can identify consistent estimates of the causal effect if the majority of SNPs are valid instruments. Currently, only developed for continuously measured outcomes. 

References

• Kang H, Zhang A, Cai TT, Small DS. Instrumental Variables Estimation With Some Invalid Instruments and its Application to Mendelian Randomization. Journal of the Americal Statistics Association 2016;111:132-142.

Other terms in 'Pleiotropy-robust one-sample MR methods':

• MR GENIUS
• MR GxE
• PRMR
• Two-stage Hard Thresholding (TSHT) with voting