Generalized Propensity using Computer Learning Methods in High Dimensional and Nonlinear Data

3187 

Contributed Abstract 

Poster 

Jonathan Baldwin (1), Kai Ding (1), Sixia Chen (2)

(1) University of Oklahoma Health Sciences Center, OKC, OK, (2) Univeristy of Oklahoma Health Sciences Center, OKC, OK

Kai Ding  
University of Oklahoma Health Sciences Center

Sixia Chen  
Univeristy of Oklahoma Health Sciences Center

Jonathan Baldwin  
University of Oklahoma Health Sciences Center

Jonathan Baldwin  
N/A

Introduction: Few studies have examined performance of the generalized propensity score (GPS) in estimating average treatment effects (ATE) using computer learning methods in high dimensional and nonlinear data. Objective: Use simulation to assess causal inference bias when applying multiple computer learning estimated GPSs in high dimensional and nonlinear data. Methods: A large population was simulated with four covariates associated with a continuous treatment, and a continuous outcome. Extraneous covariates were simulated for total of four dimensionality scenarios. Additionally, treatment associations were simulated in a linear and non-linear fashion. 1000 Monte Carlo datasets were randomly selected and GPS was estimated using multiple linear and computer learning algorithms (including but not limited to random forest, SVM, and deep learning). ATE was assessed for each model type, and compared using bias and absolute percent relative bias from known population effects. Expected Results: Common linear model methods will perform well in linear low dimensional scenarios, computer learning methods will outperform in high dimensionality and nonlinearity.

Generalize Propensity Score |Machine Learning|High Dimensional|Non-Linear| |

Section on Statistics in Epidemiology

Causal Inference