SearcharxivSearch

arXiv · 2609.17908

Cross Validation for the log Gaussian Cox Process

Abstract

The log Gaussian Cox Process (LGCP) is one of the most widely used models for the analysis of spatial point patterns. Although Bayesian methods and software for fitting LGCPs are now well established, practical tools for model criticism, predictive assessment, and model comparison remain comparatively underdeveloped. This paper develops a practical Bayesian cross-validation framework for LGCPs while placing it within a broader framework for Bayesian model assessment. Our approach is motivated by the conceptual and computational challenges that arise when defining predictive validation for point processes, including the choice of holdout data, prediction task, scoring rule, and computational strategy. We propose a leave-region-out cross-validation framework in which the fundamental unit of prediction is a bounded spatial region rather than an individual event. Predictive performance is assessed through the logarithmic scoring rule for joint probabilistic forecasts, while computational efficiency is achieved by combining a new likelihood approximation with a Bayesian unlearning strategy and Laplace approximations to obtain leave-region-out predictive distributions without repeated model refitting. We validate the proposed approximations against Monte Carlo estimates obtained via brute-force refitting, demonstrate the methodology on simulated and real spatial point pattern datasets defined on Euclidean domains and networks, and provide implementations in the R-INLA, inlabru, and MetricGraph packages.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hans Montcho, Håvard Rue, Finn Lindgren, David Bolin, Elias T Krainski, Daniela Castro-Camilo, Sara Martino. 2026-09-15. Cross Validation for the log Gaussian Cox Process. https://arxiv.org/abs/2609.17908

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Considerations for the Integration of Randomized Controlled Trials and Real-World Data

As clinical decision-making increasingly moves toward individualized and context-specific treatment recommendations, reliance on any single evidence source, randomized or observational, may be insufficient. Principled integration of randomized controlled trials and real-world data, grounded in explicit causal frameworks, offers a path toward evidence that is both internally credible and externally relevant. In this article, we describe distinct objectives for the integration of randomized controlled trials and real-world data and discuss how these objectives shape key design and analytic considerations, illustrating the resulting choices through example estimands. We highlight practical issues that commonly arise in applied settings, including data relevance and curation, cross-source comparability, estimand specification, and sensitivity analysis. We aim for this article to help readers evaluate and implement principled approaches to integrating randomized controlled trials and real-world data in ways that can support more reliable treatment recommendations while maintaining regulatory-grade evidentiary standards.

stat.ME

Validity of MMRM-based hypothesis testing under missing-not-at-random mechanisms

In randomized clinical trials with longitudinal continuous outcomes, missing-not-at-random (MNAR) missingness often motivates conservative alternatives to mixed models for repeated measures (MMRM). Such caution is important for estimation, but estimation and testing need not require identical assumptions. Moreover, overly conservative primary analyses may reduce power, increase required sample size, and raise trial costs. We investigated the validity of MMRM-based testing under the global null of identical longitudinal outcome distributions across groups. Because valid testing minimally requires treatment-effect estimators to converge to the null under the null hypothesis, we investigated sufficient conditions for this property. We introduced a proportional observation condition requiring ratios of observation probabilities relative to a reference group, conditional on the full outcome vector, to be outcome-independent, and showed that, with arbitrary post-baseline visits and monotone missingness, this condition is sufficient for convergence to the null value. The condition allows observation to depend on unobserved outcomes and permits between-group differences in overall observation probabilities through outcome-independent dropout, making it clinically interpretable while accommodating outcome-dependent MNAR missingness. Synthetic and data-based bootstrap simulations showed negligible bias and empirical test sizes near 0.05, including nonmonotone missingness. Thus, MNAR missingness does not by itself imply that a more conservative primary testing procedure is required. This result does not justify treatment-effect estimation under alternatives, which still requires estimand-based interpretation and sensitivity analyses.

stat.ME

Optimized variance estimation under interference and complex experimental designs

Unbiased and consistent variance estimators generally do not exist for design-based treatment effect estimators because experimenters never observe more than one potential outcome for any unit. The problem is exacerbated by interference and complex experimental designs. Experimenters must accept conservative variance estimators in these settings, but they can strive to minimize the conservativeness. In this paper, we show that the task of constructing a minimally conservative variance estimator can be interpreted as an optimization problem that aims to find the lowest estimable upper bound of the true variance given the experimenter's risk preferences and knowledge of the potential outcomes. We characterize the set of admissible bounds in the class of quadratic forms, and we demonstrate that the optimization problem is a convex program for many natural objectives. The resulting variance estimators are guaranteed to be conservative regardless of whether the background knowledge used to construct the bound is correct, but the estimators are less conservative if the provided information is reasonably accurate. Numerical results show that the resulting variance estimators can be considerably less conservative than existing estimators, allowing experimenters to draw more informative inferences about treatment effects.

stat.ME