AteMeVs: An R package for the estimation of the average treatment effect with measurement error and variable...

Area of Science:

• Biostatistics
• Computational Biology
• Genomics

Background:

• Estimating average treatment effects is crucial in causal inference, particularly in cancer research using gene expression data.
• Challenges include handling measurement error and noninformative variables in gene expression data.
• Existing analytical methods lack user-friendly computational software for implementation.

Purpose of the Study:

• To develop a user-friendly R package, AteMeVs, for estimating average treatment effects.
• To address challenges of measurement error and noninformative gene expressions in causal inference.
• To provide a computational tool extending existing methods for broader applications.

Main Methods:

• Developed an R package named AteMeVs.
• Employed inverse-probability-weighting estimation.
• Handled data with measurement error and spurious variables, accommodating Yi and Chen (2023).

Main Results:

• The AteMeVs package provides a user-friendly implementation for average treatment effect estimation.
• The package effectively handles gene expression data with measurement error and noninformative variables.
• Demonstrated utility through application to a cancer dataset.

Conclusions:

• AteMeVs fills a critical gap by offering accessible software for complex causal inference in genomics.
• The package enhances the analysis of gene expression data in cancer research.
• Facilitates broader application and implementation of advanced causal inference methods.