TSCI: Two Stage Curvature Identification for Causal Inference with Invalid Instruments in R
Open Access
- 1 January 2025
- journal article
- Published by Foundation for Open Access Statistic in Journal of Statistical Software
- Vol. 114 (7) , 1-21
Abstract
TSCI implements treatment effect estimation from observational data under invalid instruments in the R statistical computing environment. Existing instrumental variable approaches rely on arguably strong and untestable identification assumptions, which limits their practical application. TSCI does not require the classical instrumental variable identification conditions and is effective even if all instruments are invalid. TSCI implements a two-stage algorithm. In the first stage, machine learning is used to cope with nonlinearities and interactions in the treatment model. In the second stage, a space to capture the instrument violations is selected in a data-adaptive way. These violations are then projected out to estimate the treatment effect.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Causal inference with invalid instruments: post-selection problems and a solution using searching and samplingJournal of the Royal Statistical Society Series B: Statistical Methodology, 2023
- The Confidence Interval Method for Selecting Valid Instrumental VariablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2021
- Confidence Intervals for Causal Effects with Invalid Instruments by Using Two-Stage Hard Thresholding with VotingJournal of the Royal Statistical Society Series B: Statistical Methodology, 2018
- Double/debiased machine learning for treatment and structural parametersThe Econometrics Journal, 2018
- Nonparametric Additive Instrumental Variable Estimator: A Group Shrinkage Estimation PerspectiveJournal of Business & Economic Statistics, 2017
- Mendelian randomization with invalid instruments: effect estimation and bias detection through Egger regressionInternational Journal of Epidemiology, 2015
- p-Values for High-Dimensional RegressionJournal of the American Statistical Association, 2009
- Random Forests and Adaptive Nearest NeighborsJournal of the American Statistical Association, 2006
- Modern Applied Statistics with S2002
- Estimation and Simultaneous Correlation in Complete Equation Systems1992