Corresponding Editor: R. Ornduff

Abstract Kernel smoothing is routinely used for the estimation of relative risk based on point locations disease cases and sampled controls over a geographical region. Typically, fixed‐bandwidth kernel has been employed, despite widely recognized problems experienced with this methodology when underlying densities exhibit type spatial inhomogeneity frequently seen in epidemiology. A more intuitive approach to utilize spatially adaptive, variable parameter. In paper, we examine properties...

The estimation of kernel-smoothed relative risk functions is a useful approach to examining the spatial variation disease risk. Though there exist several options for performing kernel density in statistical software packages, have been very few contributions date that focused on function <em>per se</em>. Use variable or adaptive smoothing parameter individual densities has shown provide additional benefits estimating and specific computational tools this are essentially absent. Furthermore,...

Kernel smoothing is a popular approach to estimating relative risk surfaces from data on the locations of cases and controls in geographical epidemiology. The interpretation such facilitated by plotting tolerance contours which highlight areas where sufficiently high reject null hypothesis unit risk. Previously it has been recommended that these intervals be calculated using Monte Carlo randomization tests. We examine computationally cheap alternative whereby are derived asymptotic theory....

Abstract The pair correlation function (two-point correlation) of a spatial point process is fundamental tool in statistics and astrostatistics, measuring the strength dependence between points. Interest focuses on behaviour this at short distances, but region which existing estimators can be particularly unreliable. We propose new estimator based techniques from stochastic geometry kernel density estimation. Theory simulation experiments confirm that far superior to estimators, especially...

Abstract Intensity estimation through kernel smoothing is a popular non‐parametric method of describing the characteristics an underlying spatial point process. Key to accuracy this estimate choice bandwidth. Too large or small bandwidth can lead features in intensity being lost introduction artefacts. There are many available methods selection for patterns, but no consensus on best option. Popular and software default options very different estimates contrasting conclusions about data that...

This paper introduces an R package for spatial and spatio-temporal prediction forecasting log-Gaussian Cox processes. The main computational tool these models is Markov chain Monte Carlo (MCMC) the new package, <b>lgcp</b>, therefore also provides extensible suite of functions implementing MCMC algorithms processes this type. modeling framework details inferential procedures are first presented before a tour <b>lgcp</b> functionality given via walk-through data-analysis. Topics covered...

Log-Gaussian Cox processes are an important class of models for spatial and spatiotemporal point-pattern data. Delivering robust Bayesian inference this presents a substantial challenge, since Markov chain Monte Carlo (MCMC) algorithms require careful tuning in order to work well. To address issue, we describe recent advances MCMC methods these their implementation the R package lgcp. Our suite functions provides extensible framework inferring covariate effects as well parameters latent...

Summary We propose a computationally efficient and statistically principled method for kernel smoothing of point pattern data on linear network. The locations, the network itself, are convolved with two‐dimensional then combined into an intensity function This can be computed rapidly using fast Fourier transform, even large networks bandwidths, is robust against errors in geometry. estimator consistent, its statistical efficiency only slightly suboptimal. discuss bias, variance, asymptotics,...

Abstract The spatio-temporal dynamics of an outbreak provide important insights to help direct public health resources intended control transmission. They also a focus for detailed epidemiological studies and allow the timing impact interventions be assessed. A common approach is aggregate case data administrative regions. Whilst providing good visual impression change over space, this method masks spatial variation assumes that disease risk constant across space. Risk factors COVID-19 (e.g....

Researchers from Australia, New Zealand, Canada and the United States collaborated to validate their foot mouth disease models--AusSpread, InterSpread Plus North American Animal Disease Spread Model--in an effort build confidence in use as decision-support tools. The final stage of this project involved using three models simulate a number outbreak scenarios, with data Republic Ireland. scenarios included uncontrolled epidemic, epidemics managed by combinations stamping out vaccination....

The high-dimensionality typically associated with discretized approximations to Gaussian random fields is a considerable hinderance computationally efficient methods for their simulation. Many direct approaches require spectral decompositions of the covariance matrix and so are unable complete solving process in timely fashion, if at all. However under certain conditions, we may construct block-circulant versions hand thereby allowing access fast-Fourier perform required operations...

The univariate log‐Gaussian Cox process (LGCP) has shown considerable potential for the flexible modelling of spatial, and more recently, spatiotemporal, intensity functions planar point patterns within a restricted region in space. Its flexibility mathematical tractability are partly offset by need to acquire sensible estimates parameters controlling dependence structure Gaussian field given observed data. method minimum contrast, which compares theoretical descriptors with their...

Spatial point pattern data sets are commonplace in a variety of different research disciplines. The use kernel methods to smooth such is flexible way explore spatial trends and make inference about underlying processes without, or perhaps prior to, the design fitting more intricate semiparametric parametric models quantify specific effects. long-standing issue 'optimal' data-driven bandwidth selection complicated these settings by issues as high heterogeneity observed patterns need consider...

Methods have been developed for the characterization of flocculent brewer's yeast based on a modification Burns method and use an automatic recording spectrophotometer. Strains Saccharomyces spp. with known characteristics in tower continuous fermentation were used to examine methods correlate values obtained those found using method.