Sibling Regression for Generalized Linear Models

TL;DR

This paper introduces a residual-based sibling regression method to correct systematic measurement errors in generalized linear models, improving data accuracy in ecological surveys.

Contribution

It proposes a novel residual function approach that overcomes limitations of existing linear additive noise models for GLMs.

Findings

Reduces systematic detection variability in moth surveys

Effective on synthetic data

Improves data correction in ecological studies

Abstract

Field observations form the basis of many scientific studies, especially in ecological and social sciences. Despite efforts to conduct such surveys in a standardized way, observations can be prone to systematic measurement errors. The removal of systematic variability introduced by the observation process, if possible, can greatly increase the value of this data. Existing non-parametric techniques for correcting such errors assume linear additive noise models. This leads to biased estimates when applied to generalized linear models (GLM). We present an approach based on residual functions to address this limitation. We then demonstrate its effectiveness on synthetic data and show it reduces systematic detection variability in moth surveys.