Variance partitioning in spatio-temporal disease mapping models

Franco‐Villoria, Maria; Ventrucci, Massimo; Rue, Haåvard

doi:10.1177/09622802221099642

Cited by 4 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different choices of priors are also discussed in the literature [24,28,27]. [29] proposes a new parameterization of the priors for the interaction types I, II, III, and IV called variance partitioning. This parameterization includes a mixing parameter that balances the main and interaction effects, which improves interpretability.…”

Section: Prior Distributions For the Hyperparametermentioning

confidence: 99%

“…We model η η η by the classical parameterization of [1], as in (33), with RW2 and Besag models as the main structured effects. We test the four different interaction types for the interaction term and assign the PC-joint prior [29] for the hyperparameter,…”

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

“…The parameters U 1 , U 2 , a 1 , and a 2 are defined by the user. As a rule of thumb, we use U 1 = 0.5, U 2 = 1/0.31, a 1 = 0.99, and a 2 = 0.01 [24,29]. The partitions ϑ ϑ ϑ = (ϑ 1 , ϑ 2 , ϑ 3 , ϑ 4 , ϑ 5 ) of the variances are parameterized,…”

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

“…with PC priors for ϑ 1 , ϑ 2 and uniform priors for ϑ 3 , ϑ 4 ,ϑ 5 [29]. We compute the marginal posteriors of the hyperparameters and the latent field for each type using inla1234() from the INLAPLUS package to fit the four interaction types.…”

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

See 3 more Smart Citations

Approximate Bayesian Inference for the Interaction Types 1, 2, 3 and 4 with Application in Disease Mapping

Fattah¹,

Rue²

2022

Preprint

View full text Add to dashboard Cite

We address in this paper a new approach for fitting spatiotemporal models with application in disease mapping using the interaction types I, II, III, and IV proposed by [1]. When we account for the spatiotemporal interactions in disease-mapping models, inference becomes more useful in revealing unknown patterns in the data. However, when the number of locations and/or the number of time points is large, the inference gets computationally challenging due to the high number of required constraints necessary for inference, and this holds for various inference architectures including Markov chain Monte Carlo (MCMC) [2] and Integrated Nested Laplace Approximations (INLA) [3]. We re-formulate INLA approach based on dense matrices to fit the intrinsic spatiotemporal models with the four interaction types and account for the sum-to-zero constraints, and discuss how the new approach can be implemented in a high-performance computing framework. The computing time using the new approach does not depend on the number of constraints and can reach a 40-fold faster speed compared to INLA in realistic scenarios. This approach is verified by a simulation study and a real data application, and it is implemented in the R package INLAPLUS and the Python header function: inla1234().

show abstract

Section: Prior Distributions For the Hyperparametermentioning

confidence: 99%

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

Section: Spatiotemporal Variation Of Infant Mortality In Minas Gerais...mentioning

confidence: 99%

See 2 more Smart Citations

Approximate Bayesian Inference for the Interaction Types 1, 2, 3 and 4 with Application in Disease Mapping

Fattah¹,

Rue²

2022

Preprint

View full text Add to dashboard Cite

show abstract

Pandemic data quality modelling: a Bayesian approach in the Italian case

Ferrari,

Manzi,

Micheletti

et al. 2024

Qual Quant

View full text Add to dashboard Cite

When pandemics like COVID-19 spread around the world, the rapidly evolving situation compels officials and executives to take prompt decisions and adapt policies depending on the current state of the disease. In this context, it is crucial for policymakers to always have a firm grasp on what is the current state of the pandemic, and envision how the number of infections and possible deaths is going to evolve shortly. However, as in many other situations involving compulsory registration of sensitive data from multiple collectors, cases might be reported with errors, often with delays deferring an up-to-date view of the state of things. Errors in collecting new cases affect the overall mortality, resulting in excess deaths reported by official statistics only months later. In this paper, we provide tools for evaluating the quality of pandemic mortality data. We accomplish this through a Bayesian approach accounting for the excess mortality pandemics might bring with respect to the normal level of mortality in the population.

show abstract

A Variance Partitioning Multi-level Model for Forest Inventory Data with a Fixed Plot Design

Marques

Wiemann

Kneib

2023

JABES

View full text Add to dashboard Cite

Forest inventories are often carried out with a particular design, consisting of a multi-level structure of observation plots spread over a larger domain and a fixed plot design of exact observation locations within these plots. Consequently, the resulting data are collected intensively within plots of equal size but with much less intensity at larger spatial scales. The resulting data are likely to be spatially correlated both within and between plots, with spatial effects extending over two different areas. However, a Gaussian process model with a standard covariance structure is generally unable to capture dependence at both fine and coarse scales of variation as well as for their interaction. In this paper, we develop a computationally feasible multi-level spatial model that accounts for dependence at multiple scales. We use a data-driven approach to determine the weight of each spatial process in the model to partition the variability of the measurements. We use simulated and German small tree inventory data to evaluate the model’s performance.Supplementary material to this paper is provided online.

show abstract

Variance partitioning in spatio-temporal disease mapping models

Cited by 4 publications

References 43 publications

Approximate Bayesian Inference for the Interaction Types 1, 2, 3 and 4 with Application in Disease Mapping

Approximate Bayesian Inference for the Interaction Types 1, 2, 3 and 4 with Application in Disease Mapping

Pandemic data quality modelling: a Bayesian approach in the Italian case

A Variance Partitioning Multi-level Model for Forest Inventory Data with a Fixed Plot Design

Contact Info

Product

Resources

About