The topic of this article is one-sided hypothesis testing for disparity, i.e., the mean of one group is larger than that of another when there is uncertainty as to which group a datum is drawn. For each datum, the unc...The topic of this article is one-sided hypothesis testing for disparity, i.e., the mean of one group is larger than that of another when there is uncertainty as to which group a datum is drawn. For each datum, the uncertainty is captured with a given discrete probability distribution over the groups. Such situations arise, for example, in the use of Bayesian imputation methods to assess race and ethnicity disparities with certain insurance, health, and financial data. A widely used method to implement this assessment is the Bayesian Improved Surname Geocoding (BISG) method which assigns a discrete probability over six race/ethnicity groups to an individual given the individual’s surname and address location. Using a Bayesian framework and Markov Chain Monte Carlo sampling from the joint posterior distribution of the group means, the probability of a disparity hypothesis is estimated. Four methods are developed and compared with an illustrative data set. Three of these methods are implemented in an R-code and one method in WinBUGS. These methods are programed for any number of groups between two and six inclusive. All the codes are provided in the appendices.展开更多
Administrative units reflect the territorial hierarchies established within all countries of the world.The units are addressable with geocodes that provide a bijective mapping between territories and unique identifica...Administrative units reflect the territorial hierarchies established within all countries of the world.The units are addressable with geocodes that provide a bijective mapping between territories and unique identification codes.Early warning systems for natural or man-made hazards often map affected or threatened areas to administrative units to establish a spatial reference that is comprehensible to all parts of the population.Addressing these territories in an international context has several requirements,such as worldwide coverage,completeness and topicality,which must be met by geocode standards.In this paper,the practicability and suitability of international geocode standards are examined in the context of the requirements of large-scale early warning systems.This paper exposes the insufficiencies and limitations of existing geocode standards International Organization for Standardization(ISO)-3166,Second Administrative Level Boundaries data set project(SALB)and Nomenclature of the Territorial Units for Statistics(NUTS)and emphasises the suitability of the non-official hierarchical administrative subdivision codes(HASC).The analysis is framed in the context of addressing affected areas for an Indian Ocean tsunami early warning system.This system was developed within the Distant Early Warning Systems project according to the requirements of the United Nations Educational,Scientific and Cultural Organization(UNESCO)Intergovernmental Oceanic Commission for Regional Tsunami Watch Providers(RTWPs).展开更多
Range-Doppler (RD) method and Reverse-Range-Doppler (RRD) method are combined together to achieve automatic geocoding of Synthetic Aperture Radar (SAR) image quickly and accurately in the paper. The RD method is first...Range-Doppler (RD) method and Reverse-Range-Doppler (RRD) method are combined together to achieve automatic geocoding of Synthetic Aperture Radar (SAR) image quickly and accurately in the paper. The RD method is firstly used to locate the four corners of the image, then the other pixels of the image can be located by Reverse-Range-Doppler (RRD) method. Resampling is performed at last. The approach has an advantage over previous techniques in that it does not require ground control points and is independent of spacecraft attitude knowledge or control. It can compensate the shift due to the assumed Doppler frequency in SAR image preprocessing. RRD simplifies the process of RD, therefore speeds up the computation. The experimental results show that a SAR image can be automated geocoded in 30 s using the single CPU (3 GHz) with 1 G memory and an accuracy of 10 m is attainable with this method.展开更多
Malaria incidence in Perak, Malaysia has generally declined, but there remain regions of high incidence. The spatio-temporal distribution pattern of malaria in Perak was studied using Geographical Information Systems ...Malaria incidence in Perak, Malaysia has generally declined, but there remain regions of high incidence. The spatio-temporal distribution pattern of malaria in Perak was studied using Geographical Information Systems (GIS) and spatial statistical tools. Malaria data cases at the subdistrict level in Perak from 2007 to 2011 were analysed to determine the spatial and temporal distribution patterns of malaria incidence. Geographical Information Systems (GIS) and spatial statistical tools were used to identify spatial correlation in the data and malaria hot-spots. Spatial correlation was tested by using an autocorrelation method called Moran’s I. Hot spot analysis was done using Getis-Ord G*?statistic technique. Malaria incidence rates were categorized into 3 classes to map the spatial distribution. Malaria cases in Perak were geo-spatially clustered. Most of the hot spots locations were in Kenering, Ulu Kinta, Gerik and Kampar sub-districts. The prevalence of malaria among foreigners was noticeably higher than Malaysians. Improved surveillance of foreign workers can prevent outbreaks and identify high risk areas. This study implies that geographic-based mapping and information system are needed for an effective malaria control.展开更多
With the increased use of locational information,spatial location referencing and coding methods have become much more important to the mining of both geographical and nongeographical data in digital earth system.Unfo...With the increased use of locational information,spatial location referencing and coding methods have become much more important to the mining of both geographical and nongeographical data in digital earth system.Unfortunately,current methods of geocoding,based on reverse lookup of coordinates for a given address,have proven too lossy with respect to administrative and socioeconomic data.This paper proposes a spatial subdivision and geocoding model based on spatial address regional tessellation(SART).Given a hierarchical address object definition,and based on the‘region of influence’characteristics of an address,SART creates multiresolution spatial subdivisions by irregular and continuous address regions.This model reflects most of the geographical features and many of the social and economic implications for a given address.It also better reflects the way people understand addresses and spatial locations.We also propose an appropriate method of geocoding for standard addresses(SART-GC).The codes generated by this method can record address footprints,hierarchical relationships,and spatial scales in a single data structure.Finally,by applying our methods to the Shibei District of Qingdao,we demonstrate the suitability of SART-GC for multi-scale spatial information representation in digital earth systems.展开更多
In this paper, we present a framework to validate and to correct the location information in crash reports. The proposed system is composed of several modules: creation of intersection network and pre-processing, vali...In this paper, we present a framework to validate and to correct the location information in crash reports. The proposed system is composed of several modules: creation of intersection network and pre-processing, validation, snapping, updating, and manual-spotting.The proposed system utilizes GPS coordinates(latitude/longitude), primary and reference road names, primary direction, and distance to the reference road. The algorithm starts at an initial GPS coordinate provided in the crash report. Additional location information is utilized in case this coordinate does not satisfy certain criteria. After verification of the road names, the correct snapping location is determined using the primary direction and primary distance information. At the final stage, the attributes in the crash data are retrieved from the base map given the snapping point. We tested the proposed system by three different test data sets. The number of correctly identified matches and the average snapping error are calculated for assessment. The experiments show that the proposed framework is capable of geocoding the crashes up to 98% accuracy with the average of 37 feet of snapping error and 64% of the matching records have less than snapping error of 1 foot. However, we observed that considering highly specific cases as an outlier, the snapping error significantly drops. We discuss these cases in detail and propose a remedy as a future work.展开更多
文摘The topic of this article is one-sided hypothesis testing for disparity, i.e., the mean of one group is larger than that of another when there is uncertainty as to which group a datum is drawn. For each datum, the uncertainty is captured with a given discrete probability distribution over the groups. Such situations arise, for example, in the use of Bayesian imputation methods to assess race and ethnicity disparities with certain insurance, health, and financial data. A widely used method to implement this assessment is the Bayesian Improved Surname Geocoding (BISG) method which assigns a discrete probability over six race/ethnicity groups to an individual given the individual’s surname and address location. Using a Bayesian framework and Markov Chain Monte Carlo sampling from the joint posterior distribution of the group means, the probability of a disparity hypothesis is estimated. Four methods are developed and compared with an illustrative data set. Three of these methods are implemented in an R-code and one method in WinBUGS. These methods are programed for any number of groups between two and six inclusive. All the codes are provided in the appendices.
基金the DEWS Project funded by the sixth Framework Programme of the European Commission(contract number 045453).
文摘Administrative units reflect the territorial hierarchies established within all countries of the world.The units are addressable with geocodes that provide a bijective mapping between territories and unique identification codes.Early warning systems for natural or man-made hazards often map affected or threatened areas to administrative units to establish a spatial reference that is comprehensible to all parts of the population.Addressing these territories in an international context has several requirements,such as worldwide coverage,completeness and topicality,which must be met by geocode standards.In this paper,the practicability and suitability of international geocode standards are examined in the context of the requirements of large-scale early warning systems.This paper exposes the insufficiencies and limitations of existing geocode standards International Organization for Standardization(ISO)-3166,Second Administrative Level Boundaries data set project(SALB)and Nomenclature of the Territorial Units for Statistics(NUTS)and emphasises the suitability of the non-official hierarchical administrative subdivision codes(HASC).The analysis is framed in the context of addressing affected areas for an Indian Ocean tsunami early warning system.This system was developed within the Distant Early Warning Systems project according to the requirements of the United Nations Educational,Scientific and Cultural Organization(UNESCO)Intergovernmental Oceanic Commission for Regional Tsunami Watch Providers(RTWPs).
文摘Range-Doppler (RD) method and Reverse-Range-Doppler (RRD) method are combined together to achieve automatic geocoding of Synthetic Aperture Radar (SAR) image quickly and accurately in the paper. The RD method is firstly used to locate the four corners of the image, then the other pixels of the image can be located by Reverse-Range-Doppler (RRD) method. Resampling is performed at last. The approach has an advantage over previous techniques in that it does not require ground control points and is independent of spacecraft attitude knowledge or control. It can compensate the shift due to the assumed Doppler frequency in SAR image preprocessing. RRD simplifies the process of RD, therefore speeds up the computation. The experimental results show that a SAR image can be automated geocoded in 30 s using the single CPU (3 GHz) with 1 G memory and an accuracy of 10 m is attainable with this method.
文摘Malaria incidence in Perak, Malaysia has generally declined, but there remain regions of high incidence. The spatio-temporal distribution pattern of malaria in Perak was studied using Geographical Information Systems (GIS) and spatial statistical tools. Malaria data cases at the subdistrict level in Perak from 2007 to 2011 were analysed to determine the spatial and temporal distribution patterns of malaria incidence. Geographical Information Systems (GIS) and spatial statistical tools were used to identify spatial correlation in the data and malaria hot-spots. Spatial correlation was tested by using an autocorrelation method called Moran’s I. Hot spot analysis was done using Getis-Ord G*?statistic technique. Malaria incidence rates were categorized into 3 classes to map the spatial distribution. Malaria cases in Perak were geo-spatially clustered. Most of the hot spots locations were in Kenering, Ulu Kinta, Gerik and Kampar sub-districts. The prevalence of malaria among foreigners was noticeably higher than Malaysians. Improved surveillance of foreign workers can prevent outbreaks and identify high risk areas. This study implies that geographic-based mapping and information system are needed for an effective malaria control.
基金This work was supported by Key Projects in the National Science&Technology Pillar Program during the Twelfth Five-year Plan Period[grant number 2012BAH35B01]National High Technology Research and Development Program of China[grant number 2012AA12A401]。
文摘With the increased use of locational information,spatial location referencing and coding methods have become much more important to the mining of both geographical and nongeographical data in digital earth system.Unfortunately,current methods of geocoding,based on reverse lookup of coordinates for a given address,have proven too lossy with respect to administrative and socioeconomic data.This paper proposes a spatial subdivision and geocoding model based on spatial address regional tessellation(SART).Given a hierarchical address object definition,and based on the‘region of influence’characteristics of an address,SART creates multiresolution spatial subdivisions by irregular and continuous address regions.This model reflects most of the geographical features and many of the social and economic implications for a given address.It also better reflects the way people understand addresses and spatial locations.We also propose an appropriate method of geocoding for standard addresses(SART-GC).The codes generated by this method can record address footprints,hierarchical relationships,and spatial scales in a single data structure.Finally,by applying our methods to the Shibei District of Qingdao,we demonstrate the suitability of SART-GC for multi-scale spatial information representation in digital earth systems.
文摘In this paper, we present a framework to validate and to correct the location information in crash reports. The proposed system is composed of several modules: creation of intersection network and pre-processing, validation, snapping, updating, and manual-spotting.The proposed system utilizes GPS coordinates(latitude/longitude), primary and reference road names, primary direction, and distance to the reference road. The algorithm starts at an initial GPS coordinate provided in the crash report. Additional location information is utilized in case this coordinate does not satisfy certain criteria. After verification of the road names, the correct snapping location is determined using the primary direction and primary distance information. At the final stage, the attributes in the crash data are retrieved from the base map given the snapping point. We tested the proposed system by three different test data sets. The number of correctly identified matches and the average snapping error are calculated for assessment. The experiments show that the proposed framework is capable of geocoding the crashes up to 98% accuracy with the average of 37 feet of snapping error and 64% of the matching records have less than snapping error of 1 foot. However, we observed that considering highly specific cases as an outlier, the snapping error significantly drops. We discuss these cases in detail and propose a remedy as a future work.
