Workshop in Biostatistics - archive

DATE: October 1, 2015
TIME: 1:30 - 3:00 pm
LOCATION: Medical School Office Building, Rm x303
TITLE: Nonparametric Full Matching Approach to Instrumental Variables Estimation with Application to the Causal Effect of Malaria on Stunting
SPEAKER: Hyunseung Kang, Postdoctoral Fellow, Economics
Stanford Graduate School of Business

Instrumental variables (IV) methods have been widely used to determine the causal effect of a treatment, exposure, policy, or an intervention on an outcome of interest. The IV method relies on having a valid instrument, a variable that is (A1) associated with the exposure, (A2) has no direct effect on the outcome, and (A3) is unrelated to the unmeasured confounders associated with the exposure and the outcome. Mendelian randomization (MR) is an application of IV methods in genetic epidemiology where the instruments are genetic variants derived from GWAS of potential biomarkers and satisfy the three assumptions. Once valid instruments are found, standard techniques can be used to determine the causal effect of a treatment or exposure on an outcome.

The talk will provide an introduction to MR and IV, with a specific focus on discussion of the three IV assumption that are required to derive causal effects. In particular, we propose an alternative method for IV estimation based on nonparametric full matching which addresses the concern when IV assumptions are not fully met. We evaluate our new procedure on simulated data and real data concerning the causal effect of malaria on stunting among children. We estimate that the risk of stunting among children with the sickle cell trait decrease by 0.22 times the average number of malaria episodes prevented by the sickle cell trait, a substantial effect of malaria on stunting (p-value: 0.011, 95% CI: 0.044, 1).

Suggested readings:
Lawlor DA, Harbord RM, Sterne JA, Timpson N, Davey Smith G. Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Stat Med (2008). 27(8):1133-63.

Baiocchi M, Cheng J, Small DS. Instrumental variable methods for causal inference Statistics in Medicine 2014; 33(13):2297-340.

Kang H, Kreuels B, May Jurgen, Small DS. Full matching approach to instrumental variables estimation with application to the effect of malaria on stunting, preprint available on arXiv:1411.7342.