Bayesian spatially varying coefficient models in the spBayes R package

Finley, Andrew O.; Banerjee, Sudipto

doi:10.1016/j.envsoft.2019.104608

Cited by 26 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted a simulation analysis to evaluate our ability to recover an added spatial field representing the true local trend. Given results from previous work on similar classes of models (Finley et al 2015, Auger‐Méthé et al 2016, Finley and Banerjee 2020), we focused our simulations on understanding how the magnitude of spatiotemporal variation and observation error variation affect our ability to recover the local trend (details in Supporting information, or in the publicly available code used to generate these analyses). We also performed similar sensitivity analyses to verify that the magnitude of spatial variance and local trend would affect our ability to recover the local trend in predictable ways.…”

Section: Methodsmentioning

confidence: 99%

Improving estimates of species distribution change by incorporating local trends

2020

View full text Add to dashboard Cite

A common goal in ecology and its applications is to better understand how species' distributions change over space and time, yet many conventional summary metrics (e.g. center of gravity) of distribution shifts may offer limited inference because such changes may not be spatially homogenous. We develop a modeling approach to estimate a spatially explicit temporal trend (i.e. local trend), alongside spatial (temporally constant) and spatiotemporal (time‐varying) components, to compare inferred spatial shifts to those indicated by conventional metrics. This method is generalizable to many data types including presence–absence data, count data and continuous data types such as density. To demonstrate the utility of this new approach, we focus on the application of this model to a community of well‐studied marine fish species on the US west coast (19 species, representing a wide range of presence–absence and densities). Results from conventional model selection indicate that the use of the model accounting for local trends is clearly justified for over 89% of these species. In addition to making more parsimonious and accurate predictions, we illustrate how estimated spatial fields from the local trend model can be used to classify regions within the species range where change is relatively homogenous. Conventional summary metrics, such as center of gravity, can then be calculated on each such region or within previously defined biogeographic boundaries. We use this approach to illustrate that change is more nuanced than what is expressed via global metrics. Using arrowtooth flounder Atheresthes stomias as an example, the observed southward shift over time in the center of gravity is not reflective of a uniform shift in densities but local trends of decreasing density in the northern region and rapidly increasing density at the southern edge of the species' range. Thus, estimating local trends with spatiotemporal models improves interpretation of species distribution change.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving estimates of species distribution change by incorporating local trends

2020

View full text Add to dashboard Cite

show abstract

“…Longitude and latitude coordinates were projected using Albers equal-area conic projection parameters. The Bayesian spatial regression model was fit using the 'spBayes' R package (Finley and Banerjee 2020).…”

Section: Discussionmentioning

confidence: 99%

Spatiotemporal patterns of urban mosquitoes are modulated by socioeconomic status and environmental traits in the United States

Yitbarek

Chen

Celestin

et al. 2021

Preprint

View full text Add to dashboard Cite

The distribution of mosquitoes and associated vector diseases (e.g., West Nile, dengue, and Zika viruses) is likely a function of environmental conditions in the landscape. Urban environments are highly heterogeneous in the amount of vegetation, standing water, and concrete structures covering the land at a given time, each having the capacity to influence mosquito abundance and disease transmission. Previous research suggests that socioeconomic status is correlated with the ecology of the landscape, with lower-income neighborhoods generally having more concrete structures and standing water via residential abandonment, garbage dumps, and inadequate sewage. Whether these socio-ecological factors affect mosquito distributions across urban environments in the United States (US) remains unclear. Here, we present a meta-analysis of 22 paired observations from 15 articles testing how socioeconomic status relates to overall mosquito burden in urban landscapes in the United States. We then analyzed a comprehensive dataset from a socioeconomic gradient in Baltimore, Maryland to model spatiotemporal patterns of Aedes albopictus using a spatial regression model with socio-ecological covariates. The meta-analysis revealed that lower-income neighborhoods (regions making less than $50,000 per year on average) are exposed to 151% greater mosquito densities and mosquito-borne illnesses compared to higher-income neighborhoods (≥$50,000 per year). Two species of mosquito (Ae. albopictus and Aedes aegypti) showed the strongest relationship with socioeconomic status, with Ae. albopictus and Ae. aegypti being 62% and 22% higher in low-income neighborhoods, respectively. In the spatial regression analysis in Baltimore, we found that Ae. albopictus spatial spread of 1.2 km per year was significantly associated with median household income, vegetation cover, tree density, and abandoned buildings. Specifically, Ae. albopictus abundance was negatively correlated with median household income, vegetation cover, and tree density. Ae. albopictus abundance and the cover of abandoned buildings were positively correlated. Together, these results indicate that socio-ecological interactions can lead to disproportionate impacts of mosquitoes on humans in urban landscapes. Thus, concerted efforts to manage mosquito populations in low-income urban neighborhoods are required to reduce mosquito burden for the communities most vulnerable to human disease.

show abstract

“…where u is the conditional random variable, which is usually a scalar. The varying coefficient model has a broad range of applications, including longitudinal data Tang & Cheng, 2012), functional data (Zhang & Wang, 2014;Hu et al, 2019), and spatial data (Wang & Sun, 2019;Finley & Banerjee, 2020). Moreover, varying coefficient models could naturally be extended to time series contexts (Huang & Shen, 2004;Lin et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Varying Coefficient Model via Adaptive Spline Fitting

Wang¹,

Jiang²,

Liu³

2022

Preprint

View full text Add to dashboard Cite

The varying coefficient model has received wide attention from researchers as it is a powerful dimension reduction tool for non-parametric modeling. Most existing varying coefficient models fitted with polynomial spline assume equidistant knots and take the number of knots as the hyperparameter. However, imposing equidistant knots appears to be too rigid, and determining the optimal number of knots systematically is also a challenge. In this article, we deal with this challenge by utilizing polynomial splines with adaptively selected and predictorspecific knots to fit the coefficients in varying coefficient models. An efficient dynamic programming algorithm is proposed to find the optimal solution. Numerical results show that the new method can achieve significantly smaller mean squared errors for coefficients compared with the commonly used kernel-based method.

show abstract

Bayesian spatially varying coefficient models in the spBayes R package

Cited by 26 publications

References 28 publications

Improving estimates of species distribution change by incorporating local trends

Improving estimates of species distribution change by incorporating local trends

Spatiotemporal patterns of urban mosquitoes are modulated by socioeconomic status and environmental traits in the United States

Varying Coefficient Model via Adaptive Spline Fitting

Contact Info

Product

Resources

About