reengineering the sipp: the new dynamics of economic well-being system
DESCRIPTION
Reengineering the SIPP: The New Dynamics of Economic Well-being System. David Johnson Brookings/Census Roundtable Brookings Institution June 8, 2006. Goals for Roundtable. To describe our progress and options for the new Dynamics of Economic Well-being system. - PowerPoint PPT PresentationTRANSCRIPT
1
Reengineering the SIPP: The New Dynamics of Economic
Well-being System
David JohnsonBrookings/Census Roundtable
Brookings InstitutionJune 8, 2006
2
Goals for Roundtable
• To describe our progress and options for the new Dynamics of Economic Well-being system.
• To determine users’ needs for a new system, in particular, the components that are necessary to retain from the SIPP as well as the items that users are willing to give up.
3
Reengineering the SIPP
4
Goals for Dynamics of Economic Well-being system
• The value-added of the dynamics of economic well-being system is in providing a nationally representative sample that can be used to evaluate the annual and sub-annual dynamics of income, the movements into and out of government transfer programs, and the interactions between these items.
5
Goals for Dynamics of Economic Well-being system
• The Dynamics of Economic Well-being system will
– include a new survey data collection,
– require fewer resources than the current SIPP program,
– improve processing efficiency,
– be releasable to the public in a timely manner,
– integrate survey data and administrative records data
– make use of the richness of the new data collection in the American Community Survey (ACS).
6
• Department of Agriculture
– Model food stamp eligibility and participation
• Department of Health and Human Services
– Measure the economic effects of welfare reform on children and adults,
and determine "triggers" that cause people to go on or to go off
programs.
• Social Security Administration
– Model SSI benefits, and examine the effects of benefits for couples and
surviving spouses.
• Researchers
– Use both the longitudinal and cross-sectional nature of SIPP
• Census Bureau
– Produce P70 reports on Dynamics of Economic Well-being
Current Uses of SIPP
7
Purpose of SIPP
• “The two primary goals of SIPP should be to provide improved
information on the distribution of income and other economic
resources for people and families and on eligibility for and
participation in government assistance programs.”
– The Future of the Survey of Income and Program Participation, NAS, 1993
• “... [The SIPP] provides an unprecedented opportunity to
ascertain the nature of income flows and program
participation, both for relatively short periods of time and over
extended periods of time, for individuals and families as they
experience changes in household composition, income, and
labor force participation.”
– Improving National Statistics on Children, Youth and Families, 1984
8
SIPP and Administrative data
• “The planners of SIPP are to be congratulated for their intention to combine administrative data with field survey measurements. It is…clear that combining such disparate sources of information provides much richer insights into the status and behavior of individuals.”
- James Smith, Journal of Economic and Social Measurement, 1985
9
Planning the new system
• Develop new survey component– Content, Survey design, Survey instrument
• Construct cross-walk between current data needs and administrative records availability
• Develop prototype– National level and State level
• Develop data products• Work with stakeholders to determine users’
needs
10
New Survey: Basic versus supplemental products
Basic Topics
Demographics General IncomeLabor Force Health Insurance
Assets EducationProgram Participation
Child Support
Well-being Disability
Wealth
11
Possible sample sources
• There are several options for generating a sampling frame:– sampling from the Master Address File;
– sampling directly from ACS interviewed cases;
– sampling directly from administrative data;
– selecting all CPS cases matched from one ASEC to the following year’s ASEC;
– using all CPS cases in outgoing rotations (all months); and,
– using the existing SIPP sample already identified.
12
Possible modes of data collection
Mail out/mail back
Paper and pencil CAPI – computer assisted personal interviewing CATI – computer assisted telephone interviewing
13
Possible Recall Periods
4 – month recall
• 3 interviews per year
• each interview asks about each of the preceding 4 months
6 – month recall
• 2 interviews per year
• each interview asks about each of the preceding 6 months
12 – month recall (2 options)
• 1 interview per year asking about each of the preceding 12 months
• 1 interview per year and an event history calendar to derive each of the preceding 12 months
14
Administrative records successes
Medicare Enrollment Database (MEDB)
Medicare health insurance coverage
Master Beneficiary Record (MBR)
Work disability and source of general income (e.g., Social Security)
IRS 1040, 1099-INT, and 1099-DIV
Asset ownership, income/earnings from a job, profit from a business, unemployment compensation, receipt of alimony
Census Numident Demographic characteristics such as age, race, Hispanic origin, citizenship
SSA SSR Receipt of Federal/state SSI
HUD-TRACS Public housing and receipt of rent subsidies
15
Match rates between survey data and administrative SSN
50.2%
36.4%
6.9%
0.0%
20.0%
40.0%
60.0%
80.0%
100.0%
2001 CPS
SSN Verification Address Search Name Search
94%
16
First Prototype: Matching CPS and Medicaid (MSIS) data
MSIS data
Receipt of Medicaid
MSIS
No Medicaid
Match and possible receipt
CPS
Recipient 0.4% 4.5% 6.2%
CPS
Non Recipient
0.4% 84.5% 4.2%
17
First Prototype: Matching CPS and Medicaid (MSIS) data
MSIS data
Receipt of Medicaid
MSIS
No Medicaid
Match and possible receipt
CPS
Recipient 0.4% 4.5% 6.2%
CPS
Non Recipient
0.4% 84.5% 4.2%
18
First Prototype: Matching CPS and Medicaid (MSIS) data
MSIS data
Receipt of Medicaid
MSIS
No Medicaid
Match and possible receipt
CPS
Recipient 0.4% 4.5% 6.2%
CPS
Non Recipient
0.4% 84.5% 4.2%
19
Possible Data Products
CompletePublic Data
Internal filesand RDC
SyntheticData
DEWB
20
SIPP ’04 Panel Data Collection
2/04 – 9/06
2004 2005 2006 2007 2008 2009 2010
DEWB DataCollection
2009 and on
Prototype Release
2008
DEWB Planning2006 – 2009
SIPP ’04 PanelData Files Released
9/05 – 2/08
Time period covered by
SIPP ’04 Panel data files
2/04 – 9/06
Time period covered by
the prototype
2006 - 2007 Time period covered by DEWB data collection
2008
21
URL: http://www.sipp.census.gov/sipp/Source: U.S. Census Bureau, Demographics Survey Division,
Survey of Income and Program Participation branch Created: February 14, 2002 Last revised: May 10, 2006
Census Bureau Links: Home · Search · Subjects A-Z · FAQs · Data Tools · Catalog · Census 2000 · Quality · Privacy Policy · Contact Us
Assessing Users’ Needs
22
Questions • What aspects of the current SIPP do you feel are
the most important for measuring economic well-being? And In particular, what would you be willing to give up?
• Do you have examples of research (or products) that you regard as “best practices” in the use of SIPP data?
• Do you have needs for both the cross-sectional and longitudinal aspects of the data?
23
Additional slides
24
Synthetic Data:Means for various retirement income sources using actual admin data are similar to synthetic data for many demographic groups
(SIPP 2004 Panel and Monthly Benefit Amount)
0
200
400
600
800
1000
Own Retirement Disability Aged Spouse
Black Males - Admin Black Males - Synthetic
White Males - Admin White Males - Synthetic
25
Percent found by SSN verification, ADDRESS, and NAME search (CPS, SIPP and ACS)
67.5%
0.0%
36.4%17.8%
74.4%
7.7%15.1%
50.2%
6.9%
0.0%
20.0%
40.0%
60.0%
80.0%
100.0%
2001 CPS 2001 SIPP 2001 ACS
SSN Verification Address Search Name Search
94%