 |
 |
 |
 |
 |
 | |
Luc Anselin - Current Research Projects
(see also the full cv for a complete list of funded research contracts and grants)
Alan MacEachren,
Mark Gahegan, Pennsylvania
State University
Luc Anselin
Agency: National Cancer Institute
Abstract: The proposed methods and tools will facilitate
the integration of epidemiological, demographic, and health-policy data, enabling researchers
and analysts to take a holistic view of communities, their health with respect to
cancer, and relationships to health policy (e.g. screening, accessibility). A series of proof-of-concept
case studies will be used to demonstrate and assess the methods and tools developed
and, at the same time, to address specific cancer research questions relevant to
the Appalachia Cancer Network (ACN). Formal usability assessment methods will be
applied throughout the human-centered process of software design, implementation, and
deployment. The goal of these assessments will be to ensure that the methods and tools
developed are both accessible to and useable by the cancer researchers and analysts
whose work they are intended to support.
The project will take full advantage of outreach efforts
within the ACN and the Center for Spatially Integrated Social Science (CSISS), to disseminate
software developed and to provide training in its use to the cancer research and
policy communities within Appalachia and beyond.
This research project will develop, implement, assess, and disseminate the next
generation of cross-platform, visually-enabled geospatial analysis methods and tools to
support cancer-related public health research and policy. The primary objective of the
work is to develop a coordinated visual, statistical, and computational approach that extends
current abilities to explore, identify, investigate, and explain spatial patterns of cancer
incidence and mortality, and their relationships to population demographics and
health policy. Of special note are new mechanisms to assess the potential for errors of
omission and commission in that analysis.
Luc Anselin, James
Murdoch (UT Dallas), Mark
Thayer (SDSU)
Agency: National Science Foundation/Environmental Protection Agency
Abstract:
An important aspect of research underlying U.S. environmental policy is
concerned with the precise measurement of the relation between the concentration
of criteria pollutants and socio-economic and health outcomes. Among these,
aspects that have received considerable attention concern the effects
of air pollution on hospital admissions, and the effects of air pollution
on early mortality. In this study, we propose to assess the methodological
tradeoffs from the explicit incorporation of space-time dependence
in traditional air pollution "concentration-response" functions. The anticipated
increase in precision and accuracy from space-time analysis allows us
to address several key policy questions, including: what are the best
empirical measures for air pollution concentrations; what is the role
of various pollutants in explaining responses; are there no observable
effects thresholds in concentration-response functions; and what is the
range of uncertainty in the predictions from the various models.
The objective of this research is to assess the application and refinement of state of the art methods in spatial data handling (GIS), geographical analysis, spatial statistics and spatial econometrics to the effect of air quality on health outcomes, employing an extensive data base for the South Coast Air Quality Management District in Southern California. The guiding principle behind our methodological efforts is to assess the extent to which substantive impact measures are affected by choices pertaining to the identification, specification and estimation of space-time dependence. Specifically, we will focus on three aspects related to this question: (1) space-time interpolation to obtain reliable surfaces of pollutant concentrations; (2) exploratory spatial data analysis (ESDA) and visualization of model fit; and (3) estimation of space-time linear models.
To the extent that as a result of our methodological and empirical investigation we can gain improved insight into the accuracy and reduce the uncertainty from estimated models, our research will contribute to the refinement of the analysis of the costs and benefits of US environmental policy.
Michael
Goodchild, Richard
Appelbaum (UC Santa Barbara)
Luc Anselin (Software Tools Program)
Agency: National Science Foundation
Abstract:
The Center for Spatially Integrated Social Science is an project under
the National Science Foundation's program of support for the development
of research infrastructure in the social and economic sciences. The Center
provides opportunities and intellectual focus to engage social and behavioral
scientists in the explicit recognition of spatial perspectives and in
the use of spatial analytic tools. CSISS is dedicated to building a national
infrastructure for the broad dissemination of knowledge, research tools,
and learning resources within the framework of a unified spatial approach
to social science.
CSISS currently supports programs of specialist meetings, national workshops, spatial analytic tools development, best practice examples, place-based search and a virtual community.
The CSISS Software Tools Program is based in the Spatial Analysis Laboratory (SAL) in the Department of Agricultural and Consumer Economics at the University of Illinois, Urbana-Champaign. Its focus is on five areas of tools development:
- a mailing list for open source spatial data analysis software development
- a clearing house for spatial data analysis software
- Exploratory Spatial Data Analysis (ESDA) in a GIS environment
- an open source initiative for spatial data analysis software development
- web-based spatial data analysis
Luc Anselin
Agency: National Consortium on Violence Research (NCOVR) [NSF]
Abstract:
This project is to develop a suite of web-based spatial analytical tools
and support software to facilitate the study of the homicide data sets
(city and county) available to the members of the NCOVR time and space
working group. These tools include the capability to build maps, carry
out spatial queries and implement exploratory spatial data analysis (ESDA)
in a web-based environment. The tools will be designed to eventually be
integrated with NCOVR data center's web-based data delivery system and
thereby leverage existing data center efforts.
The initial functionality of the toolkit will be focused on areal data of "rates" and consist of the following:
- mapping at various scales (by county, by state, by group of counties)
- spatial queries and regular (non-spatial) queries
- spatial smoothing and mapping of rates
- outlier detection
- visualization of spatial autocorrelation (LISA maps, Moran scatterplot)
|
|
|
|
|
|
| |