English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Modern disease mapping draws upon a wealth of high resolution spatial dataproducts reflecting environmental and/or socioeconomic factors as covariates,or `features', within a geostatistical framework to improve predictions ofdisease risk. Feature selection is an important step in building these models,helping to reduce overfitting and computational complexity, and to improvemodel interpretability. Selecting only features that have a causal relationshipwith the response variable could potentially improve predictions andgeneralisability, but identifying these causal features fromnon-interventional, spatiotemporal data is a challenging problem. Here weexamine the performance of a causal feature selection procedure with regard toestimating malaria incidence in Madagascar. The studied procedure designed forthis task combines the PC algorithm with spatiotemporal prewhitening andkernel-based independence tests extended to accommodate aggregated data. Thiscase study reveals a clear advantage for causal feature selection in terms ofthe out-of-sample predictive accuracy in a forward temporal estimation task,but not in a spatiotemporal interpolation task, in comparison with thresholdedspike-and-slab, for both linear and non-linear regression models. Compared tono feature selection, causal feature selection was most beneficial in settingswherein the volume of available data was low relative to the model complexity.

Nonparametric Causal Feature Selection for Spatiotemporal Risk Mapping of Malaria Incidence in Madagascar