Non-Invariance in Nested Prediction Models under Selective Predictor Availability
Abstract
We used nested models as a framework for characterising the consequences of a selectively measured predictor in clinical prediction models. In this framework, a model containing predictors available in the target population is referred to as the restricted model, while the extended model additionally includes a selectively measured predictor. We show that non-invariance in the restricted model between selected patients and the target population decomposes into components due to omission of the additional predictor, potential residual non-invariance, and their interaction. This framework is extended to a predictor measured via multiple routes of selection resulting in collider structures. We further show that imputation based on the conditional distribution of the additional predictor in the selected population transfers the restricted-model non-invariance to the imputed extended model as imputation bias. In a forthcoming version, this framework will be illustrated using real world and simulated data. The framework provides a formal basis for understanding how selective predictor measurement affects generalisability of clinical prediction models using routinely collected health data.
Related
- Influence of continuous predictor modelling methods on prediction stability in clinical prediction model development: an empirical comparison using real clinical data
- How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction
- Abstention Spends Its Budget on Local Label Variance More Than on Novelty: Auditing Conformal Calibration and Selective Prediction under Molecular Scaffold Shift
- Locally recoverable codes from elliptic surfaces with availability and hierarchical locality
- A nested factor model for equity markets: reconciling multifractal stock returns and rough index volatilities
BibTeX
@misc{delord2026noninvariance,
title = {{Non-Invariance in Nested Prediction Models under Selective Predictor Availability}},
author = {Marc Delord},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.02836},
eprint = {2609.02836},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.02836},
}
RIS
TY - UNPB
TI - Non-Invariance in Nested Prediction Models under Selective Predictor Availability
AU - Marc Delord
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2609.02836
UR - https://arxiv.org/abs/2609.02836
AB - We used nested models as a framework for characterising the consequences of a selectively measured predictor in clinical prediction models. In this framework, a model containing predictors available in the target population is referred to as the restricted model, while the extended model additionally includes a selectively measured predictor. We show that non-invariance in the restricted model between selected patients and the target population decomposes into components due to omission of the additional predictor, potential residual non-invariance, and their interaction. This framework is extended to a predictor measured via multiple routes of selection resulting in collider structures. We further show that imputation based on the conditional distribution of the additional predictor in the selected population transfers the restricted-model non-invariance to the imputed extended model as imputation bias. In a forthcoming version, this framework will be illustrated using real world and simulated data. The framework provides a formal basis for understanding how selective predictor measurement affects generalisability of clinical prediction models using routinely collected health data.
ER -