The importance of regional models in assessing canine cancer incidences in Switzerland

Fitting canine cancer incidences through a conventional regression model assumes constant statistical relationships across the study area in estimating the model coefficients. However, it is often more realistic to consider that these relationships may vary over space. Such a condition, known as spatial non-stationarity, implies that the model coefficients need to be estimated locally. In these kinds of local models, the geographic scale, or spatial extent, employed for coefficient estimation may also have a pervasive influence. This is because important variations in the local model coefficients across geographic scales may impact the understanding of local relationships. In this study, we fitted canine cancer incidences across Swiss municipal units through multiple regional models. We computed diagnostic summaries across the different regional models, and contrasted them with the diagnostics of the conventional regression model, using value-by-alpha maps and scalograms. The results of this comparative assessment enabled us to identify variations in the goodness-of-fit and coefficient estimates. We detected spatially non-stationary relationships, in particular, for the variables related to biological risk factors. These variations in the model coefficients were more important at small geographic scales, making a case for the need to model canine cancer incidences locally in contrast to more conventional global approaches. However, we contend that prior to undertaking local modeling efforts, a deeper understanding of the effects of geographic scale is needed to better characterize and identify local model relationships.

[1]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[2]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[3]  R. Magill.  Federal Tax Administration , 1936 .

[4]  D. McFadden.  Conditional logit analysis of qualitative choice behavior , 1972 .

[5]  H. Morgenstern.  Uses of ecologic analysis in epidemiologic research. , 1982, American journal of public health.

[6]  E. Frome.  The analysis of rates using Poisson regression models. , 1983, Biometrics.

[7]  H. Checkoway,et al.  Epidemiologic programs for computers and calculators. Use of Poisson regression models in estimating incidence rates and ratios. , 1985, American journal of epidemiology.

[8]  A. Cameron,et al.  Econometric models based on count data. Comparisons and applications of some estimators and tests , 1986 .

[9]  S. Piantadosi,et al.  The ecological fallacy. , 1988, American journal of epidemiology.

[10]  A. Cameron,et al.  Regression-based tests for overdispersion in the Poisson model☆ , 1990 .

[11]  D. English.  Geographical epidemiology and ecological studies , 1992 .

[12]  F. Windmeijer,et al.  R-Squared Measures for Count Data Regression Models With Applications to Health-Care Utilization , 1996 .

[13]  F. Windmeijer,et al.  An R-squared measure of goodness of fit for some common nonlinear regression models , 1997 .

[14]  M. Charlton,et al.  Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis , 1998 .

[15]  M. Tiefelsdorf.  Modelling spatial processes : the identification and analysis of spatial relationships in regression residuals by means of Moran's I : with 32 figures and 8 talbes , 1999 .

[16]  P. Atkinson,et al.  Spatial Scale Problems and Geostatistical Solutions: A Review , 2000 .

[17]  R. Barale,et al.  Association between canine malignant lymphoma, living in industrial areas, and use of chemicals by dog owners. , 2001, Journal of veterinary internal medicine.

[18]  M. Wall.  A close look at the spatial structure implied by the CAR and SAR models , 2004 .

[19]  P. Elliott,et al.  Spatial Epidemiology: Current Approaches and Future Challenges , 2004, Environmental health perspectives.

[20]  Ronen Feldman,et al.  The Data Mining and Knowledge Discovery Handbook , 2005 .

[21]  A. Kristensen,et al.  Veterinary cancer registries in companion animal cancer: a review. , 2007, Veterinary and comparative oncology.

[22]  Jason Dykes,et al.  Geographically Weighted Visualization: Interactive Graphics for Scale-Varying Exploratory Analysis , 2007, IEEE Transactions on Visualization and Computer Graphics.

[23]  R. Berk,et al.  Overdispersion and Poisson Regression , 2008 .

[24]  M. Ceppi,et al.  Cancer incidence in pet dogs: findings of the Animal Tumor Registry of Genoa, Italy. , 2008, Journal of veterinary internal medicine.

[25]  J. J. Abellán,et al.  Methodologic Issues and Approaches to Spatial Epidemiology , 2008, Environmental health perspectives.

[26]  Peggy L. Schmidt.  Companion animals as sentinels for public health. , 2009, The Veterinary clinics of North America. Small animal practice.

[27]  F. Mutinelli,et al.  Animal tumour registry of two provinces in northern Italy: incidence of spontaneous tumours in dogs and cats , 2009, BMC veterinary research.

[28]  C. Ferguson.  An effect size primer: A guide for clinicians and researchers. , 2009 .

[29]  P. Bartlett,et al.  Disease surveillance and referral bias in the veterinary medical database. , 2010, Preventive veterinary medicine.

[30]  D. Lambert,et al.  Geographically weighted regression bandwidth selection and spatial autocorrelation: an empirical example using Chinese agriculture data , 2010 .

[31]  N. Toft,et al.  Data from the Danish Veterinary Cancer Registry on the occurrence and distribution of neoplasms in dogs in Denmark , 2010, Veterinary Record.

[32]  A. Stewart Fotheringham,et al.  Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity , 2010 .

[33]  B. Bonnett,et al.  Age patterns of disease and death in insured Swedish dogs, cats and horses. , 2010, Journal of comparative pathology.

[34]  Robert E Roth,et al.  Value-by-alpha Maps: An Alternative Technique to the Cartogram , 2010, The Cartographic journal.

[35]  D. Jolley,et al.  A poisson regression approach for modelling spatial autocorrelation between geographically referenced observations , 2011, BMC medical research methodology.

[36]  F. Lewis,et al.  A unified approach to model selection using the likelihood ratio test , 2011 .

[37]  C. E. Alvarez,et al.  Dog models of naturally occurring cancer. , 2011, Trends in molecular medicine.

[38]  R. Goldenberg,et al.  Incident Smoking during Pregnancy and the Postpartum Period in a Low-Income Urban Population , 2011, Public health reports.

[39]  J. Reif.  Animal Sentinels for Environmental and Public Health , 2011, Public health reports.

[40]  F. Gärtner,et al.  Canine tumors: a spontaneous animal model of human carcinogenesis. , 2012, Translational research : the journal of laboratory and clinical medicine.

[41]  Olaf Berke,et al.  Current status of canine cancer registration - report from an international workshop. , 2012, Veterinary and comparative oncology.

[42]  S. Leyk,et al.  Robust assessment of spatial non-stationarity in model associations related to pediatric mortality due to diarrheal disease in Brazil. , 2012, Spatial and spatio-temporal epidemiology.

[43]  Jacob van Etten,et al.  R package gdistance: distances and routes on geographical grids (version 1.1-4) , 2012 .

[44]  Ashton M. Shortridge,et al.  Measuring geographic access to health care: raster and network-based methods , 2012, International Journal of Health Geographics.

[45]  J. Dobson.  Breed-Predispositions to Cancer in Pedigree Dogs , 2013, ISRN veterinary science.

[46]  P. McGreevy,et al.  Approaches to canine health surveillance , 2014, Canine Genetics and Epidemiology.

[47]  K. Axhausen,et al.  Hundepopulation und Hunderassen in der Schweiz von 1955 bis 2008 , 2013 .

[48]  Jiming Liu,et al.  Estimating the sample mean and standard deviation from the sample size, median, range and/or interquartile range , 2014, BMC Medical Research Methodology.

[49]  Steve Weston,et al.  Provides Foreach Looping Construct for R , 2015 .

[50]  Stephane Champely,et al.  Basic Functions for Power Analysis , 2015 .

[51]  Stefan Leyk,et al.  Understanding the Combined Impacts of Aggregation and Spatial Non‐Stationarity: The Case of Migration‐Environment Associations in Rural South Africa , 2015, Trans. GIS.

[52]  Roger Bivand,et al.  Bindings for the Geospatial Data Abstraction Library , 2015 .

[53]  N. Cressie.  Inference for Lattice Models , 2015 .

[54]  K. Axhausen,et al.  The Swiss Canine Cancer Registry: a retrospective study on the occurrence of tumours in dogs in Switzerland from 1955 to 2008. , 2015, Journal of comparative pathology.

[55]  Hadley Wickham,et al.  Tools for Splitting, Applying and Combining Data , 2015 .

[56]  S. Fabrikant,et al.  A NOVEL APPROACH TO VETERINARY SPATIAL EPIDEMIOLOGY: DASYMETRIC REFINEMENT OF THE SWISS DOG TUMOR REGISTRY DATA , 2015 .

[57]  R. Bivand,et al.  Tools for Reading and Handling Spatial Objects , 2016 .

[58]  S. Fabrikant,et al.  A Regional Approach for Modeling Dog Cancer Incidences with Regard to Different Reporting Practices , 2016, GIScience 2016.

[59]  K. Axhausen,et al.  Swiss Canine Cancer Registry 1955-2008: Occurrence of the Most Common Tumour Diagnoses and Influence of Age, Breed, Body Size, Sex and Neutering Status on Tumour Development. , 2016, Journal of comparative pathology.

[60]  S. Fabrikant,et al.  Assessing effects of structural zeros on models of canine cancer incidence: a case study of the Swiss Canine Cancer Registry. , 2017, Geospatial health.