An Evaluation of Methods for Handling Missing Data in Randomized Controlled Trials with Omitted Moderation Effects

Project Information

spss
Project Status: Reviewing Applicants
Project Region: CAREERS
Submitted By: Gaurav Khanna
Project Email: myang@uri.edu
Project Institution: University of Rhode Island
Anchor Institution: CR-University of Rhode Island

Students: Elizabeth Pauley

Project Description

The overall scientific goal of this project is to evaluate methods for handling missing data in the presence of omitted moderation effects. It is an extension of a research program that evaluates multiple imputation via chained equations, multiple imputation via joint modeling and inverse probability weighting to handle missing data in randomized controlled trials with omitted moderation effects, via a simulation study.

This CAREERS project will allow for the inclusion of additional methods, and evaluate a large number of covariates (e.g., 10+). The student will dedicate time to utilize HPC (i.e., Unity) for this computational workflow i.e. to run a job, edit job code, troubleshoot coding issues, and expand her knowledge of Monte Carlo simulation studies by increasing the number of simulation conditions being examined and implementing different statistical software on Unity.

Project Information

spss
Project Status: Reviewing Applicants
Project Region: CAREERS
Submitted By: Gaurav Khanna
Project Email: myang@uri.edu
Project Institution: University of Rhode Island
Anchor Institution: CR-University of Rhode Island

Students: Elizabeth Pauley

Project Description

The overall scientific goal of this project is to evaluate methods for handling missing data in the presence of omitted moderation effects. It is an extension of a research program that evaluates multiple imputation via chained equations, multiple imputation via joint modeling and inverse probability weighting to handle missing data in randomized controlled trials with omitted moderation effects, via a simulation study.

This CAREERS project will allow for the inclusion of additional methods, and evaluate a large number of covariates (e.g., 10+). The student will dedicate time to utilize HPC (i.e., Unity) for this computational workflow i.e. to run a job, edit job code, troubleshoot coding issues, and expand her knowledge of Monte Carlo simulation studies by increasing the number of simulation conditions being examined and implementing different statistical software on Unity.