空间宗教与社会研究
- 数据、方法、技术与研究方向
Spatial Explorer of Religions and Society
- Data, Methodology, Technology and Research Agenda
密西根大学中国信息研究中心 鲍曙明
University of Michigan China Data Center Shuming Bao
New Development of Religions in China
New Clusters
贾庄土地庙落成仪式
New Fashion
New Trends
The Primary Factors for Spatial Differences in Local Religions
影响地方神信仰差异的主要因素
朱海滨：《祭祀政策与民间信仰变迁-近世浙江民間信仰研究》
上海：复旦大学出版社，2008






自然灾害 宗教与环境
产业形态 宗教与经济
交通与地理 宗教与与地理
乡土意识 宗教与文化
迁入移民 宗教与移民
巫、道文化 宗教与宗教
。。。。
宗教与历史
宗教与政治
宗教与管理
Spatial Analysis of Religions

Identify the spatial patterns of religious,
demographic and socioeconomic distribution.

Identify the spatial interactions (linkages) between
religious and other aspects of the society.

Evaluate the impacts of religions on future
development of the society.
Demand for Spatial Analysis
 How can we use the data from different sources, time,
and formats?
What is the spatial patterns of data distribution?
 How the spatial patterns changes over the time?
 How the observations are interacted over the time and
space?
 How different factors are interacted each other over the
time and space ?
Topics
1.
2.
3.
4.
5.
6.
Data
Methodology
Technology
Applications
Research Agenda
Future Directions
I. Data
Government Statistics
Census (population, economy,…)
Remote Sensing Data
Enterprises database
Geography
Information
infrastructure
for China
Studies
Financial Database
Environment
Custom Database
Household Surveys
Market Database
Statistical Data
Statistical Database:
• Monthly Statistics
• National Statistics
• Provincial Statistics
• City Statistics
• County Statistics
• Monthly Industrial Data
• Yearly Industrial Data
• Statistics on Map
• Statistical Yearbooks
Census Database:
•
Population Census 1982
•
Population Census 1990
•
Population Survey 1995,
2005
•
Province Census 2000
•
County Census 2000
•
Economic Census 2004
The Census Data of China
Population Census:
• 1953, 1964, 1982, 1990, 2000
Economic Census:
• Industrial Census (1995)
• Basic Unit Census (2001)
• Economic Census (2004)
Spatial Data of China
 2000 China Township Population Census Data with GIS Maps
 2000 China County Population Census Data with GIS Maps
(Version III)
 2000 China Province Population Census Data with GIS Maps
 2000 China Grid Population Census Data with Township
Boundaries
 China Historical Province Population Census Data with GIS
Maps (1953, 1964, 1982, 1990, 2000)
 China Historical County Population Census Data with GIS
Maps (1953, 1964, 1982, 1990, 2000)
 China 1995 Industrial Census Data with GIS Maps
 China 2001 Basic Unit Census Data with GIS Maps
 China 2004 Economic Census Data with GIS Maps
 China City Statistical Indicators with Maps (1996-)
 Geographic Layers (rivers, lakes, roads, highways, railways)
Local Gazetteers and Journal Databases
New Releases
II. Methodology
Spatial Statistics
•Tests on spatial patterns:
Tests on spatial non-stationarity
Tests on spatial autocorrelation
•Data-driven approaches (Exploratory Spatial Data Analysis)
Global Statistics
Local statistics
•Model-driven approaches
Spatial linear and non-linear models
Space-temporal models
Difference between Conventional
Statistics and Spatial Statistics
Con. statistics
Spatial statistics
•
Data:
•
Relationship: Time (yt-1, yt, yt+1)
Topology (yi-1, yi, yi+1)
•
Process:
{Z(s;t), sD(t), tT}
•
Model:
Time-series data
{Z(t), tT}
Spatial data (cross-sectional)
Y = WY + 
t   Yt  1  t
t =Y1,
2, 3, …
 - time-series
autocorrelation
wi,j = 1
if i is adjacent to j
 - spatial autocorrelation
Defining Spatial Linkage (Weights)
Criteria:
theoretical and empirical
•Accessibility (roads, rivers, railways, airlines and Internet)
•Economic linkage (commuter flows, migrations, trade
flows)
•Social linkage (college admission, language)
•Locational linkage (neighborhood, geographical
distance)
Methodology:
•Binary matrix
•Row standardized matrix
•Weight function (wij=f(x,y..))
1
2
3
4
ROW.ID COL.ID WEIGHTA
1
2
1
WEIGHTB
0 .5
1
3
1
0 .5
2
1
1
0 .33
2
3
1
0 .33
2
4
1
0 .33
3
1
1
0 .33
3
2
1
0 .33
3
4
1
0 .33
4
2
1
0 .5
4
3
1
0 .5
Identifying Spatial Trend
Theoretical Variogram:
 (h) 
1
E [( Z ( x )  Z ( x ' )) ]
2
2

Experimental Variogram:
1
 (hk ) 
Nk
 [ z ( x i )  z ( x i )]
'
2
2 | N ( h k )| i  1
hk || xi  xi ||  hk , hk 
l
'
u
1
Nk
where N(hk)={(i,j):
N(hk), or .
xi-xi_=h},
Nk
 || xi  xi ||
i 1
'
hk 
1
| hk
u

l
hk |
2
|N(hk)| is the number of distinct elements of
Nugget - represent micro-scale variation or measurement error. Its
estimated by (0).
Sill - represent the variance of the random field limh(h).
Range - the distance at which data are no longer autocorrelated.
Identifying Spatial Autocorrelation
Moran I:
n

n

I ( d )    w ij ( x i  x )( x j  x )
i
S 
2
1
n

 ( xi  x )

x
2
i
1
n
n
n
j
i
i 1
n
j
j
 xi
C ( d )  ( n  1) ( 2   w ij ) {   w ij ( x i  x j )
i
i
n
Geary C:
n
n
( S   w ij )
j
n
n
2

 ( xi  x ) 2 }
n
2
i
Moran I (Z value) is
• positive: observations tend to be similar;
• negative: observations tend to be dissimilar;
• approximately zero: observations are arranged randomly over space.
Geary C:
• large C value (>>1): observations tend to be dissimilar;
• small C value (<<1) indicates that they tend to be similar.
Identifying Local Spatial Associations
Local Moran:
n
I i ( d )   w ijZ j
ji
• significant and negative if location i is
associated with relatively low values in
surrounding locations;
• significant and positive if location i is
associated with relatively high values of
the surrounding locations.
n
Local Geary:
C i ( d )   w ij ( Z i  Z j )
2
ji
• significant and small Local Geary (t<0)
suggests a positive spatial association
(similarity);
• significant and large Local Geary (t>0)
suggests a negative spatial association
(dissimilarity).
Spatial Regression
• Spatially autoregressive model
• Spatial moving average model
• Semi-parametric model
y  W 1y  X  
   W 2  
where W1 and W2 are spatial weight matrices,  ~ N(0,).
空间数据分析理论与方法研究领域
• 空间平衡和非平衡理论 (Spatial equilibrium theories
and unequilibrium theories)
• 探索性数据分析 (Exploratory spatial data analysis)
• 空间数据抽样 (Spatial sampling)
• 地理统计学 (Geostatistics , such as multivariates
variogram and kriging)
• 局部统计分析(Local spatial statistics)
• 空间聚类分析 (Spatial cluster analysis)
• 空间数据显示 (Spatial data visualization - dynamic
visualization, statistical graphics, multi-dimensional
data visualization)
III. Technology
Functions for Spatial Analysis
 compare the data of different times
 compare the data at different locations
 aggregate the data by spatial ranges
 aggregate the data by different levels of administrative units
 integrate the data from different sources
 conduct spatial data analysis without GIS skills
 extract the data efficiently
 make the reports for ready analysis and publications
 get the local/community information for survey data analysis
 detect outliers, spatial patterns and trends
Spatial Intelligence:
An Integration of Information, Methodology and Knowledge
supported by Spatial Technology
Information
+ Methodology +
knowledge
Technology
n
w
I (d ) 
i

n
ij

( x i  x )( x j  x )
j
n
(S
2
n
w
i
j
ij
)
New Development: China Geo-Explorer
Spatial Intelligence for Space-Time Data Integration and Analysis
Charts
Statistics
Tables
Reports
Census
GIS
Maps
China Geo-Explorer
- Web Based Platform for Spatial Intelligence
Objectives:
 To provide a web-based platform for data integration and spatial
analysis
 To facilitate multidisciplinary studies and applications by brining
new methodology
 To promote knowledge sharing with new technology
Features:




Efficient data integration for spatial and non-spatial data
Quick and accurate location analysis and spatial assessment
Identify spatial patterns and trends
Generate time-saving, easy-to-use, and pre-formatted reports as
well as customized reports
 Dynamic maps for visual analysis
 Applications: proximity analysis, buffer analysis, cluster analysis,
simulation and projections,….
2000 Population Census with Maps
Spatial Hierarchical
Structure:
Province
|
Prefecture
|
County
|
Township
|
Sq km Grid
2000 Population Variables:
•
•
•
•
•
•
•
•
•
•
•
Basic Structure
Minority
Age Structure
Household
Education
Fertility
Death
Marriage
Migration
Housing
Occupation
2004 Economic Census Data with ZIP Maps
Industries
Ownerships
Revenue
Employee
…
Employee
1
1-19
20-49
50-99
100-499
500-999
1000-4999
5000-29999
30000-49999
50000+
Revenue
(10,000 Yuan)
0-30
30---50
50---100
100--300
300--500
500--1000
1000-3000
3000-5000
5000-10000
10000-30000
30000-50000
50000-100000
100000-150000
150000-200000
200000 and over
Land Use （ sq km Grid ）
Land Use Classification
土地利用分类
Cultivated Land
耕地
Forest
林地
Grassland
草地
Water
水域
Construction
城乡、工矿、居民用地
Bare Land
未利用土地
System Architecture
User
Reports
Maps
Charts
Mashup Integration
Raster Data
Vector Data
Time-Series Data
Other Data ….
Statistical Data
Observations
WFS Server
WMS Server
Google Map
GeoGlobe
Flex WebGIS
Server
Data Selection
Featured Functions
 Data Selection 数据选择 （政府统计、人口普查、经济普查、工业普查、单位普查、土地、环境）
 By administrative units (province, city, county, township)
 By groups
 By location (X&Y) and spatial range (km or miles)
 By time-series statistics (province, city and county)
 By establishments (province, city, county and ZIP)
 Reporting 报告
 Summary report 汇总报告
 Comparison report 比较报告
 Original data report 原始数据报表
 Spatial Analysis 空间分析
 Graphic analysis 图形分析 （直方图， 散点图，多变量图）
 ESDA spatial statistics 探索性空间统计分析
 OLS regression 普通回归
 Spatial Regression 空间回归
 Export 输出
 Data tables (Excel) 数据表格
 Reports (Excel, Word, PDF) 分析报告
 GIS files (Shape) 数字地图
 Maps (PDF) 打印地图
Selection by Administrative Units
行政区选择
Select by map
Select by administrative units
Selection by Groups 分组选择
Selection by Locations
按空间位置选择
Select by X & Y coordinates
Select by locations on map
Selection by Establishments 单位选择
Province and City Statistics 政府统计
Export of Space-Time Series Data
时空数据分析与输出
Exploratory Spatial Data Analysis
空间统计分析
Graphic Analysis：Histogram
Graphic Analysis：Scatter Plot
Graphic Analysis：Multi-Plots
Gravity Model for Space-time Data
Multiple Outputs 多种报告输出
Customized Reports 自定义报告输出
Output：Establishments
Output：GIS Maps
Integration with local Gazetteers
IV. 应用研究
Spatial Distribution of Regions
Spatial Structure of Religions
Spatial Trends of Religious Development
Spatial Religion and Population
Spatial Religion and Economy
Spatial Religion and Environment
Spatial Religion and Social Development
Policy Impacts on Religious Development
Location Selection of Religious Sites
Household/Field Surveys
Case Study: 宗教与社会空间研究
Reports
Web Tool
Elevation
Charts
Religious Clusters
Religious Sites
Case Study: 宗教与社会调查空间分析
VI. Research Agenda for Spatial Religions
- A New Discipline for Religions in Space and Time
- Spatial theory: demand and supply (macro and micro, national,
regional and local levels)
- Spatial data visualization and exploratory data analysis (ESDA)
of religions
- Identifying the spatial structure of religions
- Identifying the spatial patterns of religious distribution
- Identifying outliers, spatial trends and spatial regimes (one or
multiple religions)
- Spatial model analysis for the complex system
- Identifying interactions among different religions
- Identifying interactions between religion, population,
economy, culture and environment, ….
- Location selection of religious sites
- Local functions of religious service
- Spatial range of religious service
- Spatial religion and policies
- The internal governance of religions
- The local governance of religions
What is New for Spatial Religions ?
- build a bridge for humanities and social sciences
- Add new dimension of time and space to
religious studies
- Expansion from humanities to social sciences
- Expansion from one dimension to multiple
dimensions
- 宗教研究在时空上的扩展
- 人文学向社会科学的扩展
- 单维向多维研究空间的扩展
空间宗教的研究议题
空间宗教的宏观、中观和微观分析：
-宏观分析：宗教空间分布模式与变化趋势；空间宗教与经济、
技术、政策的发展联系
-中观分析：空间宗教分布扩散与区域发展联系；某一宗教信仰
的空间分布与扩散
-微观分析：地方宗教点选址决策分析、空间布局、空间服务范
围
空间宗教的方法研究：
-空间宗教分布与发展的可视化
- 空间宗教探索性数据分析
-空间宗教数据建模分析
-空间宗教变化模拟与趋势预测
空间宗教的理论分析：
-宗教的需求与供应的空间平衡分析
-不同宗教信仰的管理模式与扩散机制
-地方宗教、文化及社区体系的生态系统研究
VI. Future Directions未来方向
• 数据库扩展（地理、环境、资源、人口、经济、历史
、人文与社科研究资料库）
• 遥感影像集成分析
• 用户数据集成分析
• 个性化与专门化的应用平台
• 虚拟环境管理
• 系统模拟与预测
• 模型库
• 统计库
• 图形库
Establishing the Spatial Information Network for Religious Studies
“空间宗教信息研究” 合作网
What We Can Do with the Network?
可以量化的研究
可以规范化的研究
可以复制的研究
可以积累的研究
可以开放的研究
可以扩展的研究
人人可以从事的研究
Contact
Shuming Bao
China Data Center
University of Michigan
Suite 301, 1007 E Huron St.
Ann Arbor, MI 48104-1690 USA
Tel: (734)647-9610
Email: sbao@umich.edu
Web: http://chinadatacenter.org