Lasso Adjustments of Treatment Effect Estimates in Randomized Experiments

• Activity Number: 296
• Type: Topic Contributed
• Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Adam Bloniarz* and Cun-Hui Zhang and Hanzhong Liu and Jasjeet Sekhon and Bin Yu
• Companies: University of California at Berkeley and Rutgers University and University of California at Berkeley and University of California at Berkeley and University of California at Berkeley
• Keywords: Lasso ; Causal inference ; High-dimensional statistics ; Randomized trials ; Neyman-Rubin model

Abstract

We provide a principled way for investigators to analyze randomized experiments when the number of covariates is large. Investigators often use linear multivariate regression to analyze randomized experiments instead of simply reporting the difference of means between treatment and control groups. Their aim is to reduce the variance of the estimated treatment effect by adjusting for covariates. If there are a large number of covariates relative to the number of observations, regression may perform poorly because of overfitting. In such cases, the Lasso may be helpful. We study the resulting Lasso-based treatment effect estimator under the Neyman-Rubin model of randomized experiments. We present theoretical conditions that guarantee that the estimator is more efficient than the simple difference-of-means estimator, and we provide a conservative estimator of the asymptotic variance, which can yield tighter confidence intervals than the difference-of-means estimator.