Instrumental Variable Estimation for Compositional Treatments

TL;DR

This paper develops causal inference methods for compositional data, such as microbiome and ecological datasets, highlighting pitfalls and proposing multivariate transformations and regression techniques for valid cause-effect analysis.

Contribution

It introduces a causal framework for compositional data using instrumental variables and develops new multivariate methods that respect the data's structure.

Findings

Methods outperform traditional approaches on synthetic data

Application to real microbiome data demonstrates practical utility

Highlights pitfalls in interpreting compositional causes

Abstract

Many scientific datasets are compositional in nature. Important biological examples include species abundances in ecology, cell-type compositions derived from single-cell sequencing data, and amplicon abundance data in microbiome research. Here, we provide a causal view on compositional data in an instrumental variable setting where the composition acts as the cause. First, we crisply articulate potential pitfalls for practitioners regarding the interpretation of compositional causes from the viewpoint of interventions and warn against attributing causal meaning to common summary statistics such as diversity indices in microbiome data analysis. We then advocate for and develop multivariate methods using statistical data transformations and regression techniques that take the special structure of the compositional sample space into account while still yielding scientifically interpretable results. In a comparative analysis on synthetic and real microbiome data we show the advantages and limitations of our proposal. We posit that our analysis provides a useful framework and guidance for valid and informative cause-effect estimation in the context of compositional data.