The World of Microeconomics Data

1
The World of Microeconomics Data

• Publicly Collected
• - FedStats
• Privately Collected
• - Standards and Poors
• -Dunn Bradstreet
• -Compustat
• International Organizations
• -World Bank
• Universities
• -University of Michigan

2
Data Sources Where To Find Them

• http//www.economics.ltsn.ac.uk/links/data_free.ht
  m
• Bill Goffes website http//rfe.wustl.edu/Data/in
  dex.html
• Talk to Joel Herndon at the library
• ICPSR - http//www.icpsr.umich.edu/

3
International Infrastructure

• United Nations
• Organization for Economic Cooperation and
  Development
• Eurostat
• National Statistical Agencies

4
General Structure of International Statistical
Programs

• Data are collected by national statistical
  institutes, not the international agency
• The international agency promulgates standards
  and definitions, which are adopted (or not) by
  the national statistical institutes (e.g., U.S.
  Census Bureau)
• The international agency prepares compendia of
  statistical data and reports

5
The Top-down View

• United Nations (UN)
• World Bank/International Monetary Fund (IMF)
• International Labor Organization (ILO)
• Organization for Economic Cooperation and (OECD)
• Eurostat
• National statistical institutes (e.g., INSEE)

6
The United Nations Statistical Office

• Worldwide coverage
• Main site http//unstats.un.org/unsd/default.htm
• Public use products
• Millenium indicators http//unstats.un.org/unsd/m
  i/mi_goals.asp
• Documentation and methods http//unstats.un.org/u
  nsd/mi/mi_def_list.asp
• Sources http//unstats.un.org/unsd/mi/mi_sources_
  list.asp
• Social indicators http//unstats.un.org/unsd/demo
  graphic/social/default.htm
• Licensed products
• United Nations Statistics Common Database
  http//unstats.un.org/unsd/cdb/cdb_help/cdb_quick_
  start.asp
• Cornell documentation http//www.library.cornell.
  edu/olinuris/ref/modelun.html
• Documentation and methods http//unstats.un.org/u
  nsd/methods.htm

7
Organization for Economic Cooperation and
Development

• Covers 30 member countries representing the
  developed economies of the world
  http//www.oecd.org/document/58/0,2340,en_2649_201
  185_1889402_1_1_1_1,00.html
• Prepares standardized statistics from these
  countries using input data from official national
  sources http//www.oecd.org/statsportal/0,2639,en
  _2825_293564_1_1_1_1_1,00.html
• Public use products in print and pdf format
• Licensed products are available in Economist
  Intellegence Unit CountryData http//countrydata.
  bvdep.com/cgi/template.dll?product101useripaddr
  ess (from cornell.edu)
• Many statistics available on CDROM from OECD but
  not online.

8
World Bank/IMF

• Produce standardized national income statistics
  in the International Financial Statistics (IFS)
  database http//ifs.apdi.net/imf/ifsbrowser.aspx?
  branchROOT
• General statistics and documentation
  http//www.imf.org/external/np/sta/
• Historical data distributed by the ICPSR in the
  US

9
US Data

• Publicly Collected
• - FedStats
• Privately Collected
• - Standards and Poors
• -Dunn Bradstreet
• -Compustat
• Universities
• -University of Michigan

10
US Government

• Statistical Infrastructure
• Main players
• OMB
• Census Bureau
• BEA
• BLS
• ETA
• NIH
• CDC
• NCES
• NASS

11
Products of Statistical Systems

• National income and product accounts (SNA)
• Labor force surveys
• Population censuses
• Economic censuses
• Consistent time series
• Detailed tabular data
• Public-use products

12
Census Bureau

• decennial Census-confidential PUMS
• Business Census-confidential only
• Household Surveys-confidential PUMS
• Duke Students Are Lucky Because You Have Access
  to confidential data through the RDC.

13
Census Household Surveys

• Current Population Survey (CPS)
• Survey of Income Program Participation (SIPP)

14
Nature of the CPS

• Jointly sponsored and managed by the Bureau of
  Labor Statistics and the Census Bureau
• Official household survey for measuring the
  unemployment rate
• Produces more than 25,000 time series generically
  called the Labor Force Statistics from the CPS
• Produces more than 250,000 household-based time
  series with characteristics of the households and
  persons in the U.S. civilian non-institutional
  population

15
SIPP

• The survey design is a continuous series of
  national panels,
• Sample size ranges from approximately 14,000 to
  36,700 interviewed households.
• The duration of each panel ranges from 2 ½ years
  to 4 years.
• Collects information on income, labor force
  information, program participation

16
Linked Data

• SIPP data can be linked to Social Security Data
• Eg. Social Security Earnings Records
• Social Security Program Participation
  Information

17
Bureau of Labor Statistics - National
Longitudinal Surveys

• The National Longitudinal Surveys (NLS) are a set
  of surveys designed to gather information at
  multiple points in time on the labor market
  activities and other significant life events of
  several groups
• -young men, mature men
• -young women, mature women
• -youth

18
Difference Between Confidential Public Data

• Public Domain
• Variables are topcoded or suppressed
• Aggregated from the person or household level to
  county level
• Sample of recipients

• Government Records /Confidential Data
• No Topcoding or Suppression of Variables
• No Aggregation get person level records
• Full Sample
• ECONOMIC DATA

19
Economic Data

• Business establishments or firms
• Tabulations of these data are often publicly
  available
• Public use microdata files do not exist because
  of difficulty in maintaining confidentiality
  while preserving economic content of the data

20
Economic Datasets

• Annual Survey of Manufactures
• Census of Construction
• Census of Finance and Insurance
• Census of Manufactures
• Census of Mining
• Census of Real Estate
• Census of Retail
• Census of Services
• Census of Transportation
• Census of Wholesale
• Characteristics of Business Owners Survey
• Commodity Flow Survey

• Large Company Survey-Auxiliary Establishment
  Survey
• Longitudinal Research Database
• Manufacturing Energy Consumption Survey
• Medical Expenditure Panel Survey, Insurance
  Component
• National Employer Survey
• Pollution Abatement Costs and Expenditures
• Quarterly Financial Reports
• Research and Development Survey
• Survey of Manufacturing Technology

21
Available Economic Datasets

• Longitudinal Research Database (LRD)
• annual cost and output data on manufacturing
  establishments (plants)
• collected every five years
• contains over 1,000,000 distinct establishments
• can be linked to other economic datasets,
  including the Pollution Abatement Costs and
  Expenditures survey
• see http//www.ces.census.gov/ces.php/abstract?pap
  er100107

22
Available Economic Datasets

• Economic Census
• Conducted every five years, 1977-1997
• Surveys business establishments in all sectors of
  the economy
• Includes information about location, operating
  receipts and sources of receipts, revenues,
  expenses, employment, and payroll

23
Interesting Research Conducted Using Confidential
Census Data

• Patrick Bayer Yale University
• Michael Greenstone MIT
• Chad Syverson University of Chicago
• Sam Kortum University of Minnesota
• John Haltiwanger-University of Maryland
• And many others

24
University Collected Data

• University of Michigan
• Health And Retirement Survey (HRS)
• Panel Study of Income Dynamics
• Duke University
• National Longterm Care Survey

25
Economics 310

• A New Course Offered At Duke
• Introduces students to the world of data
  available to them and the basics required to
  acquire and transform raw information into social
  and economic data.

26
What will this class teach?

• Where to find good data both public
  confidential sources
• How to get your hand on these data
• How to manage and use it

27
Options for Taking this Course

• For Credit
• Advantages
• -Eligibility for graduate student fellowships
  from the RDC network.
• -Develop a 15 page proposal. A step towards
  defending your prospectus.
• For Audit
• -You still learn all the material but are not
  required to do the homework/proposal.
• -You have to attend all the classes. 

28
Cornell Schedule

• Instruction Begins Monday January 24
• Spring Break Begins, 110 PM Saturday March 19
  Instruction Resumes, 730 AM Monday March 28 Last
  Day of Classes Saturday May 7
• The Class operates on the Cornell Schedule.
• -If you cannot attend over Duke spring break you
  can watch a taped version of the class.
• -Class ends on May 4 - after the Duke semester is
  over.
•  

29
Course Outline

• To see the course outline go to
• www.blackboard.cornell.edu
• Click on course catalog and type in info747
• The course Social and Economic Data will come up
  click on it and you will find all the course
  materials listed

30
Syllabus

• You will find a syllabus using the link defined
  above

31
Instructor John Abowd

• Edmund Ezra Day Professor of Industrial and Labor
  Relations, Department of Labor Economics, School
  of Industrial and Labor Relations, Cornell
  University
• Director, Cornell Institute for Social and
  Economic Research (CISER)
• Distinguished Senior Research Fellow, United
  States Census Bureau
• Research Associate, National Bureau of Economic
  Research

32
Interested Participants

• Come by and see Susan Chen in Room 327E Social
  Sciences
• Call Susan at 660-6892
• Email Susan at schen_at_econ.duke.edu
• You will need a permission number to enroll.