Local standardized incidence ratio estimates and comparison with other mapping methods for small geographical areas using Slovenian breast cancer data

Tina Žagar, Vesna Zadnik and Maja Primic Žakelj

Journal of Applied Statistics, 2011, vol. 38, issue 12, 2751-2761

Abstract: Cancer maps are important tools in the descriptive presentation of the cancer burden. The objective is to explore the advantages and disadvantages of mapping methods based on point data in comparison with maps based on aggregated data. Four types of maps were prepared based on the same underlying data set on breast cancer incidence in Slovenian females, 2002--2004. First, the standardized incidence ratios (SIR) by municipalities are mapped in a traditional way. Second, two maps applying widely used smoothing methods are presented, both based on aggregated municipalities’ data: floating weighted averages and the Bayesian hierarchical modelling. Finally, the new alternative method based on exact cancer cases and population coordinates is applied -- called the local SIR estimates. The decreasing west to east trend is visible on all map types. Smoothing produced more stable and less noisy SIR estimates. The map of the local SIR estimates emphasizes extremes, but unlike the map, based on the observed SIR, these estimates are statistically stable, enabling more accurate evaluation. The main advantages of local SIR estimates over the other three methods are the abilities of revealing more localized patterns and ignoring the arbitrary administrative borders. The disadvantage is that the geocoded data are not always available.

Date: 2011
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664763.2011.570314 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:38:y:2011:i:12:p:2751-2761

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664763.2011.570314

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().