Modeling Bronchiolitis Incidence Proportions in the Presence of Spatio-Temporal Uncertainty

Heaton, Matthew J.; Berrett, Candace; Pugh, Sierra; Evans, Amber; Sloan, Chantel D.

doi:10.1080/01621459.2019.1609480

Cited by 5 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This data limitation requires more rigorous statistical methods to address the spatial uncertainty issue directly during estimation. Similar problems have been confronted in other research areas (e.g., Zimmerman et al, 2007;Chakraborty and Gelfand, 2010;Fanshawe and Diggle, 2011;Heaton et al, 2019), yet these solutions may not be suitable here. First, many of these models rely on restrictive models of the spatial…”

Section: Results For Nigeriamentioning

confidence: 90%

Flexible multivariate spatio-temporal Hawkes process models of terrorism

Jun¹,

Cook²

2022

Preprint

View full text Add to dashboard Cite

We develop flexible multivariate spatio-temporal Hawkes process models to analyze patterns of terrorism. Previous applications of point process methods to political violence data mainly utilize temporal Hawkes process models, neglecting spatial variation in these attack patterns. This limits what can be learned from these models as any effective counter-terrorism strategy requires knowledge on both when and where attacks are likely to occur. Even the existing work on spatio-temporal Hawkes processes imposes restrictions on the triggering function that are not well-suited for terrorism data. Therefore, we generalize the structure of the spatio-temporal triggering function considerably, allowing for nonseprability, nonstatitionarity, and cross-triggering (i.e., across the groups). To demonstrate the utility of our models, we analyze two samples of real-world terrorism data: Afghanistan (2002Afghanistan ( -2013 for univariate analysis and Nigeria (2009-2017) for bivariate analysis. Jointly, these two studies demonstrate that our models outperform standard Hawkes process models, besting widely-used alternatives in overall model fit and revealing spatio-temporal patterns that are, by construction, masked in these models (e.g., increasing dispersion in cross-triggering over time).

show abstract

Section: Results For Nigeriamentioning

confidence: 90%

Flexible multivariate spatio-temporal Hawkes process models of terrorism

Jun¹,

Cook²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Accounting for this uncertainty could be of scientific interest. However, a clear method to account for this uncertainty is not directly available, but various methods have been proposed (see, e.g., Heaton et al 2018a).…”

Section: Discussionmentioning

confidence: 99%

“…For this research, we treated the modeled values of X 1 (s, t) and X 2 (s, t) as known. Notably, the uncertainty of these predictions could be accounted for using methods similar to Heaton et al (2018a). However, implementing such an approach would not only be computationally cumbersome but also introduce further identifiability issues in our model due to the product of the kernel with these values in Eq.…”

Section: Spatiotemporal Model For Soil Water Contentmentioning

confidence: 99%

Spatiotemporal Lagged Models for Variable Rate Irrigation in Agriculture

Pugh

Heaton

Svedin

et al. 2019

JABES

Self Cite

View full text Add to dashboard Cite

Irrigation is responsible for 80-90% of freshwater consumption in the USA. However, excess water demand, drought, declining groundwater levels, and water quality degradation all threaten future water supplies. In an effort to better understand how to efficiently use water resources, this analysis seeks to quantify the effect of soil water at various depths on the eventual crop yield at the end of a season as a lagged effect of space and time. As a novel modeling contribution, we propose a multiple spatiotemporal lagged model for crop yield to identify critical water times and patterns that can increase the crop yield per drop of water used. Because the crop yield data consist of nearly 20,000 observations, we propose the use of a nearest neighbor Gaussian process to facilitate computation. In applying the model to soil water and yield in Grace, Idaho, for the 2016 season, results indicate that soil moisture in the 0-0.3 m depth of soil was most correlated with crop yield earlier in the season (primarily during May and June), while the soil moisture at the 0.3-1.2 m depth was more correlated with crop yield later in the season around mid-June to mid-July. These results are specific to a crop of winter wheat under center-pivot irrigation, but the model could be used to understand relationships between water and yield for other crops and irrigation systems.Supplementary materials accompanying this paper appear online.

show abstract

“…The regionalization used in this research shown in Figure was chosen as a trade‐off between the ability to capture important features in spatial variability of the bronchiolitis season, the degree of statistical learning of the change point model, and computational tractability. While our regionalization was useful here to discover spatial variations in the seasonal pattern of bronchiolitis over a large spatial domain, this partition is likely too large to be able to estimate other important drivers of the bronchiolitis seasons such as pollution levels that operate at finer spatial scales . In this regard, further research is warranted on the choice of regionalization so that these important factors could be included in a regression model for the peak bronchiolitis rates, or, potentially, a spatial partition could be learned from the data via some form of a Dirichlet process mixture model, but this avenue is left open for future research.…”

Section: Discussionmentioning

confidence: 99%

“…Because p ( s ) is unknown, the integral in is also unknown. Heaton et al treat p ( s ) as an additional unknown parameter estimated from the data, but doing so here would require calculating at each iteration of our MCMC algorithm that vastly increases the computation required for model inference. Alternatively, p ( s ) could be approximated by some known population distribution (eg, from the US census) so that calculation of could be done outside the MCMC algorithm.…”

Section: A Spatio‐temporal Change Point Modelmentioning

confidence: 99%

Estimating seasonal onsets and peaks of bronchiolitis with spatially and temporally uncertain data

Pugh

Heaton

Hartman

et al. 2019

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

RSV bronchiolitis (an acute lower respiratory tract viral infection in infants) is the most common cause of infant hospitalizations in the United States (US). The only preventive intervention currently available is monthly injections of immunoprophylaxis. However, this treatment is expensive and needs to be administered simultaneously with seasonal bronchiolitis cycles in order to be effective. To increase our understanding of bronchiolitis timing, this research focuses on identifying seasonal bronchiolitis cycles (start times, peaks, and declinations) throughout the continental US using data on infant bronchiolitis cases from the US Military Health System Data Repository. Because this data involved highly personal information, the bronchiolitis dates in the dataset were "jittered" in the sense that the recorded dates were randomized within a time window of the true date. Hence, we develop a statistical change point model that estimates spatially varying seasonal bronchiolitis cycles while accounting for the purposefully introduced jittering in the data. Additionally, by including temperature and humidity data as regressors, we identify a relationship between bronchiolitis seasonality and climate. We found that, in general, bronchiolitis seasons begin earlier and are longer in the southeastern states compared to the western states with peak times lasting approximately 1 month nationwide.

show abstract

Modeling Bronchiolitis Incidence Proportions in the Presence of Spatio-Temporal Uncertainty

Cited by 5 publications

References 53 publications

Flexible multivariate spatio-temporal Hawkes process models of terrorism

Flexible multivariate spatio-temporal Hawkes process models of terrorism

Spatiotemporal Lagged Models for Variable Rate Irrigation in Agriculture

Estimating seasonal onsets and peaks of bronchiolitis with spatially and temporally uncertain data

Contact Info

Product

Resources

About