Spatial demography

In response to growing evidence that official population statistics based on the decennial census are inaccurate and not fit-for-purpose at the Local Authority level - the fundamental administrative unit of the UK, the author has established an innovative method of using locally available administrative data sets for estimating populations. The method combines different data sources with different population coverage according to a defined set of rules. The result is timelier and geographically flexible data which is more cost-effective to undertake than a survey-based census. The ONS in the UK are now committed to exploring the use of administrative data as a replacement for the traditional survey-based census, and their findings are to be given in 2014. Key to this is the linkage of disparate datasets that are captured for other purposes to determine when the same entity (person) is present. This paper presents the author’s experience of linking administrative datasets and investigates how geography is not only the common link, but also an inherent bias that affects matching rates in terms of neighbourhood effects such as population turnover and ethnic diversity. An optimised algorithm for linking local administrative datasets is put forward, based on the results of sensitivity analyses.

By applying the cluster analysis technique and Heligman-Pollard mortality model, the present paper aims to study the regional variations in mortality age patterns of EAG states including Assam in India for the most recent period 2010-11. The study exploited data from sample registration system 1996-2010 and Annual Health Survey 2010-11. It discovers the four clusters explaining different patterns of age specific mortality. Also identifies the two districts Dindori of state Madhya Pradesh and Chitrakoot of Uttar Pradesh having their own mortality pattern and this is true for males as well as for females also. It is found that there is considerable intra district variation in mortality patterns. Results clearly point out that united approach of health policies will not work properly and henceforth will not help in reducing mortality. Thus on the basis of findings study recommends not only for macro level as well as for micro level health policies and program.

Urbanization has greatly altered the distribution of world’s cities. While the number of cities has been mushrooming from all corners of the world, the greatest number of cities and the largest cities today are increasingly found in the developing world. We use the 2011 Revision of the World Urbanization Prospects to compute population centroids of world’s cities from 1950 to 2025. We find that the world centroid has had a southeastward trajectory after 1950. The surface distance of the centroid in 2010 was 2150 km away from that in 1950. Asia has the greatest impact on the evolution of the population centroid of world cities than other major areas. Only the US (in the whole study period) and China (after 1990) ever altered this trajectory. The trajectory of population centroid of world cities is in line with that of their geographic centroid, whereas it differs from that of their economic centroid. Trajectories of the demographic centroids for major areas and countries are also discussed. The changes of population centroids will definitely have important socioeconomic and environmental consequences at local, regional or global levels.

Population projections at a small area level are sensitive to random departures in temporal trends of population change components. In order to have robust trends for the county level projections in Costa Rica, the team in charge of forecasting decided to determine county clusters based on the past trends. In this paper, we compare three descriptive techniques used to build space-time clusters for the Crude Birth Rate: Functional Data Analysis (FDA), the scan statistic, and Geographically Weighted Regression GWR. GWR was the technique that yielded clusters related to the diffusion paradigm for fertility decline. However, the scan statistic provided a more parsimonious set of clusters that are more tractable for population projections.

This paper presents the map unmarried cohabitation in the Americas. The map offers a large scale cross-national perspective together with small area estimates of cohabitation. Census microdata from 41 countries and more than 17,000 units have been pulled together to map the percentage of cohabitation among women in union aged 25 to 29. From Canada to Argentina, results show inter- and intra-national contrasting regional patterns. The highest rates of cohabitation are found in areas of Central America, the Caribbean, Colombia and Peru. The lowest rates are mainly found in the United States and Mexico. Brazil, Argentina and Chile occupy intermediate positions. In all countries, there is substantial spatial heterogeneity, as indicated by spatial autocorrelation statistics. Our results beg the question as to which forces have shaped these patterns and remind us that such forces need to be taken into account to understand recent patterns and rises in cohabitation.

Demographic phenomena show spatial regularity and specific patterns which need to be studied. Development of GIS and Geodatabase brought maps common, and recent developments of spatial analysis allow going further than mapping to measure spatial structure. Neighborhood and scale are two dimensions of demographic data which can’t be no longer ignored.

This paper proposes an original exploration of spatial dimensions of demographic variables (density, proportion of 65+in the population, proportion growth) through the systematic analysis of French census data at various scales (6 administrative divisions) and times (6 censuses from 1968 to 2007).

Using moran’s I and LISA, we consider the effects of scales and neighborhood on spatial patterns. The results underline the necessity to better take space into account in statistical analysis.

The measurement of spatial segregation phenomena has been mainly studied in the United States since the 1950’s. A multitude of segregation indexes have been elaborated to analyze all the aspects of this topic. In 1988, Massey and Denton synthetized the scientific knowledge by a 5-dimensional classification: evenness, exposure, concentration, centralization and clustering. This presentation displays us to demonstrate that these dimensions can be approached by a single index: the Duncan’s segregation index (1955). By using a method of spatial decomposition of the index, the proposed methodology allows to free itself from the aspatial character of the index and to create a map representation which visually reproduces the spatial structure of the phenomenon. Applied to the French urban areas this methodology allows demonstrating that the spatial structure of segregation is organized according to a sectorial model (Hoyt) for socioeconomic criteria, and follows a concentric model (Burgess) for sociodemographic criteria.

Depopulation is feared by European and western countries as it often signals a society in decline. This paper will examine the question of depopulation, decline and demographic ageing in the countries of southern Europe at infra-national level. It will be divided into three parts. First, we will identify the regions affected by depopulation. We will then construct a typology of territories in demographic decline based on changes over time in population numbers by sex and by age group. Last, cartographic analysis will be used to verify whether the depopulation process follows a particular spatial logic.
This study will be based primarily on census data (age-sex structure) collected at various administrative levels in each country of the study region. We will also use base maps available at several infra-national levels. In addition, our theoretical knowledge of territorial grids and the associated problems (MAUP) will help us to establish our own grid and to avoid certain types of bias in our statistical and cartographic analysis.

Over the last two decades significant progress has been made in the development of probabilistic population forecasting methods, and many applications to countries and global regions are now in evidence. Unfortunately little interest has been shown in the extension of these methods to subnational areas. Given that forecast error is inversely related to population size, coupled with the fact that much planning occurs at the local and regional scale, the need to quantify forecast uncertainty for subnational regions is arguably even greater than at the national scale. This paper presents a regional probabilistic population and household projection for Sydney, Australia’s largest metropolitan region and home to about 4.6 million people. A bi-regional framework is adopted consisting of the region of interest and the rest of the country; predictive intervals for fertility, mortality, internal migration, international migration and living arrangements are formulated on the basis of time series models, past errors and expert judgement. The results demonstrate the considerable extent of forecast uncertainty for the region, and reveal how the official high-low projection range provides a misleading indication of uncertainty. The paper concludes by discussing how probabilistic forecasts might be applied in metropolitan regional planning.

We modify original queen based spatial weight matrix manually. Our result of spatial weight matrix is based on the combination of the simple (queen based) contiguity and the k-nearest neighbor based contiguity. Local Indicator of Spatial Autocorrelation (LISA) displays clusters and outliers. Clusters are shown in red (High-High value) and blue (Low-Low value). Other values (High-Low and Low-High) are respectively shown in light red and light blue. Regional demographic indicators are spatially autocorrelated significant at p=0.05. Distribution of each variable is by nature clustered rather than dispersed or random. Districts with relatively high value demographic indicators tend to be located near other relatively high value ones. District with relatively low value demographic indicators in each variables tend to be located near other relatively low values ones. Significant location of rural variable clusters are in western Java province, eastern Java province, eastern Nusa Tenggara province and south-eastern Sulawesi province. Significant locations of life expectancy hot spot are in Java island, while cold spots are located in Papua island.

Key words: spatial weight matrix, spatial data analysis, clusters