Deterministic Leave-One-Cluster-Out Cross-Validation for Multilevel Bayesian Structural Equation Models
Abstract
We introduce a closed-form, refit-free procedure for leave-one-cluster-out (LOCO) cross-validation in multilevel Gaussian Bayesian structural equation models (SEMs), together with predictive scoring of every nested submodel. Conditional independence of clusters given the parameters expresses the cluster-deleted posterior as a functional of the full posterior. The LOCO predictive density is then a harmonic mean of the cluster likelihood, computable from a single fit in INLAvaan, the integrated nested Laplace approximation package for Bayesian SEM. We evaluate the harmonic-mean expectation in closed form through a fully exponential Laplace approximation of the reciprocal cluster likelihood under a Gaussian posterior; candidate structural restrictions follow by Gaussian conditioning of the same Laplace summary. The resulting Taylor elpd (expected log predictive density) scores are fully deterministic, requiring neither refitting nor Monte Carlo sampling, so the variance pathology of the naive harmonic-mean estimator does not arise. A direct-sum decomposition of the compound-symmetric cluster covariance makes the cost independent of cluster size, orders of magnitude below brute-force refitting. We validate against brute-force refits and Markov chain Monte Carlo in simulation, and illustrate the procedure on school-safety climate in PISA 2022 and on 16 candidate structures linking personality and well-being in the MIDUS sibling sample.
Related
- Impact analysis of institutional framework and policy preferences with Bayesian structural equation
- Amortized Bayesian Inference on Multilevel Models of Arbitrary Structure
- A Bayesian framework for multilevel data under model mis-specification
- Sequential Entropic Optimal Transport for Bayesian Inverse Problems via Multilevel Monte Carlo
- A tutorial on selecting, translating, and reporting variance priors in Bayesian multilevel models.
BibTeX
@misc{alhyari2026deterministic,
title = {{Deterministic Leave-One-Cluster-Out Cross-Validation for Multilevel Bayesian Structural Equation Models}},
author = {Mohammad Alhyari and Haziq Jamil and Hans Montcho and Håvard Rue},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00670},
eprint = {2609.00670},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00670},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Deterministic Leave-One-Cluster-Out Cross-Validation for Multilevel Bayesian Structural Equation Models
AU - Mohammad Alhyari
AU - Haziq Jamil
AU - Hans Montcho
AU - Håvard Rue
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00670
UR - https://arxiv.org/abs/2609.00670
AB - We introduce a closed-form, refit-free procedure for leave-one-cluster-out (LOCO) cross-validation in multilevel Gaussian Bayesian structural equation models (SEMs), together with predictive scoring of every nested submodel. Conditional independence of clusters given the parameters expresses the cluster-deleted posterior as a functional of the full posterior. The LOCO predictive density is then a harmonic mean of the cluster likelihood, computable from a single fit in INLAvaan, the integrated nested Laplace approximation package for Bayesian SEM. We evaluate the harmonic-mean expectation in closed form through a fully exponential Laplace approximation of the reciprocal cluster likelihood under a Gaussian posterior; candidate structural restrictions follow by Gaussian conditioning of the same Laplace summary. The resulting Taylor elpd (expected log predictive density) scores are fully deterministic, requiring neither refitting nor Monte Carlo sampling, so the variance pathology of the naive harmonic-mean estimator does not arise. A direct-sum decomposition of the compound-symmetric cluster covariance makes the cost independent of cluster size, orders of magnitude below brute-force refitting. We validate against brute-force refits and Markov chain Monte Carlo in simulation, and illustrate the procedure on school-safety climate in PISA 2022 and on 16 candidate structures linking personality and well-being in the MIDUS sibling sample.
ER -