Academic Data Centre
We have data and are willing to help
you use it
Who we are
• The ADC provides the
following services:
– Access to statistical and
geospatial data
– One-on-one consultations
for
• Finding statistics and
geospatial files
• Using statistics and GIS
software (SPSS, SAS, ArcGIS
etc.)
• Running statistical methods
and spatial analyses
– In-class instruction and
online tutorials
Room 1104, Leddy Library (next to
Williams' Coffee Pub).
Micro and Macro
• Microdata is about individuals, macrodata is
about populations
• Macrodata (“statistics”) is country, state or
region level data such as employment rate,
GDP, infant mortality, etc.
• Microdata (“raw data”) is data on individual
people or units such as households, stocks or
firms
Primary and Secondary Data
• Primary data: data you collect yourself, to
answer your specific research question
• Secondary data: data collected by some other
researcher or institution which you are
repurposing to answer your research question
– May be used as main focus of research or provide
supplementary information
Geospatial data?
• Geospatial data is the
composite of spatial
data and attribute data,
describing:
– Attribute information:
What is it?
– Location information:
Where is it?
• Macro and
environmental data are
good for mapping
Building
Type: Office
Height: 100 ft.
Condition: Good
Where does data come from?
• Public: governments, inter-governmental organizations like
the UN and the World Bank
– Censuses, Statistics Canada, U.N. Multiple Indicator Surveys,
Spatial, Environment (water samples, emissions, climate)
• Non-profit: NGOs, charities, think tanks
– International Food Policy Research Institute, Pew Research
Centre
• Academic: individual researchers and research
collaborations
• Private: media, corporations etc. collect data
– Gallup and other polls are archived; non-news related private
data is usually hard to obtain
Public vs. private: it’s the money
• Publically funded institutions have a mandate
to spend their money towards certain goals
and are held accountable to the public
• Private institutions / businesses have no such
mandate and are not accountable beyond
what is required by law
• Most publically available data comes from
public institutions and the occasional
interested and persistent researcher
Statistics on business, industry and
economics
• Companies prefer to not give data away, unless
required by law (government industry statistics),
required by shareholders (company reports), or as
a result of interacting with other entities (e.g. stock
market)
• Three main sources:
– governmental (including IGO)
– companies themselves
– published business / industry analysis and trade
statistics
Government Data
Statistics Canada and others
National Data Collection
• Every country (more or less) has a census
• Conducted at 5 or 10 year intervals
• Since a complete sample, often the only source for
very small area data
• Most developed countries also conduct a number
of large scale surveys (economic / employment,
health, etc.)
• Countries also collect data for administrative
purposes (trade, tax, voting records, immigration
etc.)
Canada
• National Statistics Agency: Statistics Canada
– Collect or compile statistics on demographics, health, economics,
agriculture…
• Turned over collection of some health statistics (hospital based
records in particular) to Canadian Institute for Health Information
• Public Health Agency of Canada tracks data on threats to public
health, including diseases and injuries. Has the Canadian Incidence
Studies of Reported Child Abuse and Neglect
• Individual government departments also may release statistics that
they have collected for their own purposes – e.g. C.I.C. tracks
immigration statistics
• Provinces don’t have provincial statistical agencies per se, but again
departments may compile and release some data
Getting Microdata
• Public-Use Microdata Files (PUMFs) released
through Data Liberation Initiative, can be
downloaded through ODESI or Equinox .
• Restricted-Use data files can be accessed
through our Research Data Centre
• Not all Statistics Canada data is made
available though the RDCs (or at all); see lists
of available RDC data here and here.
• CIHI – see their Graduate Student Data
Access Program
Environmental: Canada
• National Pollutant Release Inventory (NPRI)
Databases
• Environment Canada Indicators
– Canadian Environmental Sustainability Indicators
– Adjusted and Homogenized Canadian Climate
Data
– Air Quality and Ozone Levels
United States
• Multiple statistical agencies – no centralized
collection or distribution point
–
–
–
–
–
Census Bureau
National Center for Health Statistics
Bureau of Labor Statistics
Bureau of Economic Analysis
National Center for Education Statistics
• U.S. public use government data tends to be
more detailed than Canadian (has detail that in
Canada would be restricted)
• U.S. restricted data is sometimes not allowed to
leave the country.
Environmental: U.S.
• Environmental Protection Agency
– Emissions & Generation Resource Integrated
Database
– National Emissions Inventories
• National Oceanic and Atmospheric
Administration
– Earth System Research Laboratory
– National Geophysical Data Center
Other Countries
• Most other (non-U.S.) countries have national
statistical agencies
– U.K.: Office for National Statistics
– Australia: Bureau of Statistics…
• The official statistical agency is generally the one that
does the census
• Some countries have national data archives that will
archive government and other data
– UK National Data Archive
– Australian Data Archive
International data: inter-governmental,
nonprofit non-governmental
What?
• Intergovernmental Organizations / IGOs
– International, established by treaty or charter e.g. U.N., World
Bank, OECD…
• Non-Governmental (NGOs)
– Non-profits, may be associated with one of the above, may be
national or international, e.g. Amnesty International,
Demographic and Health Surveys, International Food Policy
Research Institute
• In less developed countries, these are a primary
source for population welfare data that in
developed countries is collected by the
government
• Also good source for international comparative
data
Basic Sources
• Population, Economic, infrastructure etc:
– U.N. Data – data.un.org
– World Bank’s World Development Indicators and Global Development
Finance (and others)
• Health:
– World Health Organization
• A primary source for diseases, mortality, risk factors
– DOLPHN: Data Online for Population, Health and Nutrition (USAID)
• Draws on W.H.O., DHS, various other survey as well as government sources
• Environment:
– U.N. Environmental Data Explorer
– Center for International Earth Science Information Network
Environmental Sustainability Index and Population, Landscape, and
Climate Estimates (PLACE)
Major Population Welfare survey
series
• Living Standards Measurement Surveys (World Bank)
– Focus: consumption and income, good demographics
– Coverage: 40+ mostly middle-income countries
• Demographic and Health Surveys (organization of the same
name)
– Focus: health, particularly reproductive
– Coverage: 90: low- and middle-income countries, good
demographics
• Multiple Indicator Cluster Surveys (United Nations / Unicef)
– Focus: child health and welfare, reproductive health; limited
demogrpahics
– 65+ low and middle income countries
Academic Research Data
Using the data of researchers who
had better funding than you
Really big
• World Values Surveys
– Survey of the “basic values and beliefs of the publics
of more than 80 societies”
• Global Barometer and the Barometers
– Includes Afrobarometer, Arab Barometer, Asian
Barometer, and Latinobarometro. Eurobarometer is
separate.
• International Social Survey Programme
• Comparative Study of Electoral Systems
– Collaborative program of research among election
study teams from around the world.
Individual researchers and smaller
projects
• ICPSR is the world's largest archive of social
science data – more than 8,500 research studies.
– International in focus but majority of the data is
American.
– Individual researchers generally choose whether or
not to deposit their data – and under what restrictions
– Features to note: special topic archives, variables
database
• Canadian Opinion Research Archive
• Harvard’s Murray Archive / Lives Over Time
– Source for some major longitudinal studies
For assistance
• Academic Data Centre
• Email: libdata@uwindsor.ca
• Web: http://leddy.uwindsor.ca/adc