Inference Based on Kernel Estimates of the Relative Risk Function in Geographical Epidemiology

Hazelton, Martin L.; Davies, Tilman M.

doi:10.1002/bimj.200810495

Cited by 68 publications

(83 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For time interval 2, the area with an increased RR showed a tendency of expansion predominantly to the north. For both time intervals, the clusters (P = 0.001) identified by the spatial scan test were almost congruent with the areas of significantly increased RR according to Hazelton and Davies (2009). The RRs (inside cluster versus outside cluster) of the clusters as determined by the scan statistic were RR = 41.2 (interval 1) and RR = 18.5 (interval 2), respectively.…”

Section: Evaluation Of Spatial Variation In Rrsupporting

confidence: 55%

“…The same bandwidth was used for interpolation of cases as well as all samples (Diggle et al, 1995), with an edge correction performed as proposed previously (Diggle, 1985). Regions with significantly increased RR were detected and highlighted by calculating P-value contour lines as described by Hazelton and Davies (2009). Calculations were performed using the "R" packages map tools, "sm" and "sparr" in R 2.12.2 (R Development Core Team, 2011).…”

Section: Spatio-temporal Evaluation Of Relative Riskmentioning

confidence: 99%

See 1 more Smart Citation

Spatio-temporal analysis of the progression of Aujeszky’s disease virus infection in wild boar of Saxony-Anhalt, Germany

et al. 2013

View full text Add to dashboard Cite

Abstract. Aujeszky's disease (AD, pseudorabies) is a notifiable disease caused by Suid herpesvirus 1 (SuHV-1), also named pseudorabies virus (PrV). The study aimed at determining the occurrence and spatio-temporal trend of specific antibodies to AD virus (ADV) among wild boar of Saxony-Anhalt, a landlocked federal state situated in the western part of eastern Germany. To this end, a total of 7,209 blood samples were collected and tested from 2000 to 2011. An average seroprevalence of 6.8% was found for the entire observation period, whilst seroprevalence increased significantly between time periods January 2000-March 2009 (n = 3,605; prevalence = 4.5%) and March 2009-December 2011 (n = 3,604; prevalence = 9.1%). Spatial analysis revealed an extremely heterogenous distribution of seropositive samples with cluster formation [relative risk (RR) up to 41, P = 0.001] in the east. A comparison of spatial clusters between the aforementioned time intervals showed an expansion of the disease in the north to north-westerly direction. A test for spatial shift involving the entire territory of Saxony-Anhalt detected a spread of ADV infection in the latter direction (P = 0.079) at the average speed of 3.3 km/year. Detailed study of the distribution and spread of the disease among wild boar, including assessment of the speed of spatial spread, has not been done in the region before. Saxony-Anhalt has been officially recognised as being free of AD in domestic pigs since 1996. Despite increasing ADV seroprevalences in the wild boar population of Saxony-Anhalt and other federal states in the east of Germany, no spill-over to domestic pigs have been reported. The currently implemented monitoring will be continued in conjunction with surveillance of classical swine fever (CSF) to further trace ADV infections in the wild boar population of Saxony-Anhalt.

show abstract

Section: Evaluation Of Spatial Variation In Rrsupporting

confidence: 55%

Section: Spatio-temporal Evaluation Of Relative Riskmentioning

confidence: 99%

Spatio-temporal analysis of the progression of Aujeszky’s disease virus infection in wild boar of Saxony-Anhalt, Germany

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Variance estimation and interval estimation of ρ(x) then depend on the distribution of the estimatorB(u) and on the joint distribution of the observations x i withB(·). Examples of this analysis arise in case-control studies in spatial epidemiology [38,43,44].…”

Section: Constant Value ρ(X) ≡ 1 Corresponds To the Baseline Or Null mentioning

confidence: 99%

“…An exception is the special case of spatial relative risk or spatial residual risk where the covariates are the Cartesian coordinates [12,13,25,38,43,44] and/or the time coordinate [28,57]. Nonparametric estimation is important here because simple parametric models are inappropriate, and the sample size is large.…”

Section: Introductionmentioning

confidence: 99%

Nonparametric estimation of the dependence of a spatial point process on spatial covariates

Baddeley

Chang

Song

et al. 2012

Statistics and Its Interface

View full text Add to dashboard Cite

In the statistical analysis of spatial point patterns, it is often important to investigate whether the point pattern depends on spatial covariates. This paper describes nonparametric (kernel and local likelihood) methods for estimating the effect of spatial covariates on the point process intensity. Variance estimates and confidence intervals are provided in the case of a Poisson point process. Techniques are demonstrated with simulated examples and with applications to exploration geology and forest ecology.

show abstract

“…This was done using a procedure based on the calculation of asymptotic P-values assigned to each grid cell of the surface and was based on the Z-test (Hazelton and Davies, 2009). This approach is an alternative to the computationally intensive calculation of point-wise p-values using Monte Carlo simulation (Diggle, 2003;Bivand et al, 2008).…”

Section: Spatial Odds Of CM and Spatial Distribution Of Poor Ud Scorementioning

confidence: 99%

Spatial patterns of recorded mastitis incidence and somatic cell counts in Swedish dairy cows: implications for surveillance

et al. 2011

View full text Add to dashboard Cite

Abstract. Clinical mastitis (CM) is the most common veterinary treated disease in Swedish dairy cattle. To investigate if the distribution of veterinary registered cases of CM in Sweden follows that of the spatial distribution of cows with high somatic cell counts (SCCs), the spatial distribution of CM odds was estimated from available records and compared with udder health measures based on measurements of SCC derived from official milk recording. The study revealed areas with significantly lower odds for CM but with a high proportion of cows with a poor udder health score, suggesting an under-reporting of CM. We also found areas of significantly higher odds for CM despite a low proportion of cows with a poor udder health score, suggestive of over-treatment of mastitis. The results should enable targeted studies of reasons for discrepancies, e.g. farmers' and veterinarians' attitudes to mastitis treatment and disease recording in areas with a deficit or excess of registered CM cases. High quality disease records for dairy cattle are of interest not only for the dairy management but also for disease surveillance, monitoring of use of antibiotics and food safety purposes.

show abstract

Inference Based on Kernel Estimates of the Relative Risk Function in Geographical Epidemiology

Cited by 68 publications

References 26 publications

Spatio-temporal analysis of the progression of Aujeszky’s disease virus infection in wild boar of Saxony-Anhalt, Germany

Spatio-temporal analysis of the progression of Aujeszky’s disease virus infection in wild boar of Saxony-Anhalt, Germany

Nonparametric estimation of the dependence of a spatial point process on spatial covariates

Spatial patterns of recorded mastitis incidence and somatic cell counts in Swedish dairy cows: implications for surveillance

Contact Info

Product

Resources

About