Home  About us  Contact
 

Geographical Analysis (geographical + analysis)

Distribution by Scientific Domains
Humanities and Social Sciences71%

Selected Abstracts

Beyond Mule Kicks: The Poisson Distribution in Geographical Analysis

GEOGRAPHICAL ANALYSIS, Issue 2 2006
Daniel A. Griffith
The Poisson model, discovered nearly two centuries ago, is the basis for analyses of rare events. Its first applications included descriptions of deaths from mule kicks. More than half a century ago the Poisson model began being used in geographical analysis. Its initial descriptions of geographic distributions of points, disease maps, and spatial flows were accompanied by an assumption of independence. Today this unrealistic assumption is replaced by one allowing for the presence of spatial autocorrelation in georeferenced counts. Contemporary statistical theory has led to the creation of powerful Poisson-based modeling tools for geographically distributed count data. [source]

On the Application of Inductive Machine Learning Tools to Geographical Analysis

GEOGRAPHICAL ANALYSIS, Issue 2 2000
Mark Gahegan
Inductive machine learning tools, such as neural networks and decision trees, offer alternative methods for classification, clustering, and pattern recognition that can, in theory, extend to the complex or "deep" data sets that pervade geography. By contrast, traditional statistical approaches may fail, due to issues of scalability and flexibility. This paper discusses the role of inductive machine learning as it relates to geographical analysis. The discussion presented is not based on comparative results or on mathematical description, but instead focuses on the often subtle ways in which the various inductive learning approaches differ operationally, describing (1) the manner in which the feature space is partitioned or clustered, (2) the search mechanisms employed to identify good solutions, and (3) the different biases that each technique imposes. The consequences arising from these issues, when considering complex geographic feature spaces, are then described in detail. The overall aim is to provide a foundation upon which reliable inductive analysis methods can be constructed, instead of depending on piecemeal or haphazard experimentation with the various operational criteria that inductive learning tools call for. Often, it would appear that these criteria are not well understood by practitioners in the geographic sphere, which can lead to difficulties in configuration and operation, and ultimately to poor performance. [source]

The effect of smoking on the male excess of bladder cancer: A meta-analysis and geographical analyses

INTERNATIONAL JOURNAL OF CANCER, Issue 2 2009
Marjolein Hemelt
Abstract Smoking is considered the primary risk factor for bladder cancer. Although smoking prevalence and bladder cancer incidence vary around the world, bladder cancer is on average 4 times more common in males than in females. This article describes the observed male,female incidence ratio of bladder cancer for 21 world regions in 2002 and 11 geographical areas during the time period 1970,1997. A meta-analysis, including 34 studies, was performed to ascertain the increased risk for bladder cancer in males and females when smoking. The summary odds ratios (SORs) calculated in the meta-analysis were used to estimate the male,female incidence ratio of bladder cancer that would be expected for hypothetical smoking prevalence scenarios. These expected male,female incidence ratios were compared with the observed ratios to evaluate the role of smoking on the male excess of bladder cancer. The male,female incidence ratio of bladder cancer was higher than expected worldwide and over time, based on a smoking prevalence of 75% in males, 10% in females and an increased risk (SOR) of bladder cancer associated with smoking of 4.23 for males and 1.35 for females, respectively. This implied that, at least in the Western world, smoking can only partially explain the difference in bladder cancer incidence. Consequently, other factors are responsible for the difference in bladder cancer incidence. © 2008 Wiley-Liss, Inc. [source]

Beyond Mule Kicks: The Poisson Distribution in Geographical Analysis

GEOGRAPHICAL ANALYSIS, Issue 2 2006
Daniel A. Griffith
The Poisson model, discovered nearly two centuries ago, is the basis for analyses of rare events. Its first applications included descriptions of deaths from mule kicks. More than half a century ago the Poisson model began being used in geographical analysis. Its initial descriptions of geographic distributions of points, disease maps, and spatial flows were accompanied by an assumption of independence. Today this unrealistic assumption is replaced by one allowing for the presence of spatial autocorrelation in georeferenced counts. Contemporary statistical theory has led to the creation of powerful Poisson-based modeling tools for geographically distributed count data. [source]

On the Application of Inductive Machine Learning Tools to Geographical Analysis

GEOGRAPHICAL ANALYSIS, Issue 2 2000
Mark Gahegan
Inductive machine learning tools, such as neural networks and decision trees, offer alternative methods for classification, clustering, and pattern recognition that can, in theory, extend to the complex or "deep" data sets that pervade geography. By contrast, traditional statistical approaches may fail, due to issues of scalability and flexibility. This paper discusses the role of inductive machine learning as it relates to geographical analysis. The discussion presented is not based on comparative results or on mathematical description, but instead focuses on the often subtle ways in which the various inductive learning approaches differ operationally, describing (1) the manner in which the feature space is partitioned or clustered, (2) the search mechanisms employed to identify good solutions, and (3) the different biases that each technique imposes. The consequences arising from these issues, when considering complex geographic feature spaces, are then described in detail. The overall aim is to provide a foundation upon which reliable inductive analysis methods can be constructed, instead of depending on piecemeal or haphazard experimentation with the various operational criteria that inductive learning tools call for. Often, it would appear that these criteria are not well understood by practitioners in the geographic sphere, which can lead to difficulties in configuration and operation, and ultimately to poor performance. [source]

IDEAS FROM AUSTRALIAN CITIES: RELOCATING URBAN AND SUBURBAN HISTORY

AUSTRALIAN ECONOMIC HISTORY REVIEW, Issue 1 2009
Andrew May
Melbourne; suburbia; urban history This article draws on preliminary research into the social history of Melbourne, on the ways that suburban life in the post-World War II era provides both explanation and counterweight to persistently negative stereotypes of suburbia. Over recent decades, suburban histories have been eschewed in favour of historical reconsiderations of the inner city or the bush. The history of the Australian suburb, particularly since 1945, is yet to be written. Oral history and municipal archives will be crucial to the writing of such histories. The article suggests several research pathways, including intergenerational life stories, a wider scale of geographical analysis, and a subtler reading of cultural conformity and social differentiation. [source]

Bergmanns's size cline in New Zealand marine spray zone spiders (Araneae: Anyphaenidae: Amaurobioides)

BIOLOGICAL JOURNAL OF THE LINNEAN SOCIETY, Issue 1 2010
BRENT D. OPELL
Members of the spider genus Amaurobioides are restricted to the spray zone of rocky marine coasts, where they construct and hunt from silk retreats. Collecting for this study shows these spiders to be distributed around the entire New Zealand coast. A Templeton, Crandall, and Sing (TCS) analysis of the ND1 mitochondrial gene places specimens from the North Island and the northern half of the South Island into a group distinct from Amaurobioides maritima O.P.-Cambridge, 1883, which is restricted to the southern half of the South Island. Females of this northern group exhibit latitude- and temperature-related clines in body length, body mass, and residual index of condition, with larger individuals with greater indices of condition being found at cooler, southern sites. This size cline also appeared in a broader geographical analysis that included Amaurobioides piscator Hogg, 1909 from the sub-Antarctic Auckland and Campbell Islands. Thirteen ND1 haplotypes are represented in the northern group. Both independent contrast analyses and standard regressions of the mean body lengths and mean masses of these haplotypes, and the mean latitudes and temperatures of the sites where haplotypes were present, document a Bergmann's size cline, and provide evidence for an underlying genetic component. © 2010 The Linnean Society of London, Biological Journal of the Linnean Society, 2010, 101, 78,92. [source]