Overview of the SIPP Program
BACKGROUND
The Survey of Income and Program Participation (SIPP) provides a major expansion
in the kind and amount of information available to analyze the economic situation
of households and persons in the United States. The information supplied by this
survey is expected to provide a better understanding of the level, and changes in
the level, of well-being of the population and of how economic situations are
related to the demographic and social characteristics of individuals. The data
collected in SIPP will be especially useful in studying Federal transfer programs,
estimating program cost and effectiveness, and assessing the effect of proposed
changes in program regulations and benefit levels. Analysis of other important
national issues such as tax reform, Social Security program costs, and national
health insurance can be expanded and refined, based on the information from this
new survey.
The first interviews in the SIPP took place in October 1983, nearly 8 years after
the research and developmental phase, the Income Survey Development Program
(ISDP), was initiated by the Department of Health, Education, and Welfare, in
1975. Between 1975 and 1980 extensive research was undertaken to design and test
new procedures for collecting income and related socioeconomic data on a subannual
basis in a longitudinal framework. Much of the work centered around four
experimental field tests that were conducted in collaboration with the Bureau of
the Census to examine different concepts, procedures, questionnaires, and recall
periods. Two of the tests were restricted to a small number of geographic sites;
the other two were nationwide. In the first nationwide test, the 1978 Research
Panel, approximately 2,000 households were interviewed. Because of the relatively
small number of interviews, controlled experimental comparisons of alternatives
were not possible; however, the panel did demonstrate that many new ideas and
methods were feasible. It also laid a foundation for the largest and most
complex test: the 1979 Research Panel. This panel consisted of a nationally
representative sample of 8,200 households and provided a vehicle for feasibility
tests and controlled experiments of alternative design features.
In the fall of 1981, virtually all funding for ISDP research and planning of the
continuing SIPP program was deleted from the budget of the Social Security
Administration. The loss of funding for fiscal year 1982 brought all work on the
survey to a halt. In fiscal year 1983, however, money for initiation of the
survey was allotted in the budget of the Bureau of the Census. Work began
almost immediately in preparation for the survey start in October 1983. The
design of the questionnaire for the first interview was similar in structure to
that used in the 1979 ISDP panel study with two important exceptions. First,
the reference period for the questions was extended from 3 months to 4 months in
order to reduce the number of interviews and, therefore, lower costs. Second,
the questions covering labor force activity were expanded in order to provide
estimates that were closer, on a conceptual basis, to those derived from the
Current Population Survey (CPS). The design also incorporated a number of other
modifications resulting from experience with the 1979 pilot study.
SURVEY CONTENT
There are three basic elements contained in the overall design of the survey
content. The first is a control card that serves several important functions.
The control card is used to record basic social and demographic characteristics
for each person in the household at the time of the initial interview. Because
households are interviewed a total of eight or nine times, the card is also
used to record changes in characteristics such as age, educational attainment,
and marital status, and to record the dates when persons enter or leave the
household. Finally, during each interview, information on each source of income
received and the name of each job or business is transcribed to the card so that
this information can be used in the updating process in subsequent interviews.
The second major element of the survey content is the core portion of the
questionnaire. The core questions are repeated at each interview and cover
labor force activity, the types and amounts of income received during the four-
month reference period, and participation status in various programs. Some of
he important elements of labor force activity are recorded separately for each
week of the period. Income recipiency and amounts are recorded on a monthly
basis with the exception of amounts of property income (interest, dividends,
rent, etc.). Data for these types of income are recorded as totals for the four-
month period. The core also contains questions covering attendance in
postsecondary schools, private health insurance coverage, public or subsidized
rental housing, low-income energy assistance, and school breakfast and lunch
participation.
The third major element is the various supplements or topical modules that will
be included during selected household visits. The topical modules cover areas
that need not be examined every four months. Certain of these topical modules
are considered to be so important that they are viewed as an integral part of
the overall survey. Other topical modules have more specific and more limited
purposes. A list of topical modules includes work history, health
characteristics (including disability), assets and liabilities, pension plan
coverage, housing characteristics, child care, child support agreements, support
for nonhousehold members, program participation history, reasons for not working,
calender year income and benefits, taxes, and education and training.
SAMPLE DESIGN
The sample design for the first SIPP panel in 1984 consisted of about 20,000
households selected to represent the noninstitutional population of the United
States. The most recent 1993 panel has a sample size of approximately 20,000
households. Households in this SIPP panel are scheduled to be interviewed at
four-month intervals over a period of 3 years. Table A-1 shows the sample design
for the 1993 panel. The reference period for the questions is the four-month
period preceding the interview. For example, households interviewed in February
1993 were asked questions for the months October, November, December 1992, and
January 1993. This household was interviewed again in June 1993 for the February
through May period. The sample households within a given panel are divided into
four samples of nearly equal size. These subsamples are called rotation groups
and one rotation is interviewed each month. In general, one cycle of four
interviews covering the entire sample using the same questionnaire is called a
wave. This design was chosen because it provides a steady work load for data
collection and processing.
SIPP panels have been introduced in February of each year succeeding the 1984
panel. This overlapping design provides a larger sample size from which cross-
sectional estimates can be made. The overlap also enhances the survey's ability
to measure change by lowering the standard errors on differences between
estimates for two points in time.
Table A-1. Design of the 1993 SIPP Panel
Interview
Rotation Wave Month Reference Months
2 1 Feb. 93 Oct., Nov., Dec. (92), Jan. (93)
3 1 March 93 Nov., Dec. (92), Jan., Feb. (93)
4 1 April 93 Dec. (92), Jan., Feb., Mar. (93)
1 1 May 93 Jan., Feb., Mar., Apr., (93)
2 2 June 93 Feb., Mar., Apr., May (93)
3 2 July 93 Mar., Apr., May, Jun. (93)
4 2 Aug. 93 Apr., May., Jun., Jul. (93)
1 2 Sept. 93 May, Jun., Jul., Aug. (93)
2 3 Oct. 93 Jun., Jul., Aug., Sept. (93)
3 3 Nov. 93 Jul., Aug., Sept., Oct. (93)
4 3 Dec. 93 Aug., Sept., Oct., Nov. (93)
1 3 Jan. 94 Sept., Oct., Nov., Dec. (93)
2 4 Feb. 94 Oct., Nov., Dec. (93), Jan. (94)
3 4 March 94 Nov., Dec. (93), Jan., Feb. (94)
4 4 April 94 Dec. (93), Jan., Feb., Mar. (94)
1 4 May 94 Jan., Feb., Mar., Apr. (94)
2 5 June 94 Feb., Mar., Apr., May (94)
3 5 July 94 Mar., Apr., May, Jun. (94)
4 5 Aug. 94 Apr., May, Jun., Jul. (94)
1 5 Sept. 94 May, Jun., Jul., Aug. (94)
2 6 Oct. 94 Jun., Jul., Aug., Sept. (94)
3 6 Nov. 94 Jul., Aug., Sept., Oct. (94)
4 6 Dec. 94 Aug., Sept., Oct., Nov. (94)
1 6 Jan. 95 Sept., Oct., Nov., Dec. (94)
2 7 Feb. 95 Oct., Nov., Dec. (94), Jan. (95)
3 7 March 95 Nov., Dec. (94), Jan., Feb. (95)
4 7 April 95 Dec. (94), Jan., Feb., Mar (95)
1 7 May 95 Jan., Feb., Mar., Apr. (95)
2 8 June 95 Feb., Mar., Apr., May (95)
3 8 July 95 Mar., Apr., May, Jun. (95)
4 8 Aug. 95 Apr., May, Jun., Jul. (95)
1 8 Sept. 95 May, Jun., Jul., Aug. (95)
2 9 Oct. 95 Jun., Jul., Aug., Sept. (95)
3 9 Nov. 95 Jul., Aug., Sept., Oct. (95)
4 9 Dec. 95 Aug., Sept., Oct., Nov. (95)
1 9 Jan. 96 Sept., Oct., Nov., Dec. (95)
SURVEY OPERATIONS
Data collection operations are managed through the Census Bureau's 12 permanent
regional offices. A staff of interviewers assigned to SIPP conducts interviews
by personal visit each month with most interviewing completed during the first 2
weeks of that month. Completed questionnaires are transmitted to the regional
offices where they undergo an extensive clerical edit before being entered into
the Bureau's SIPP data processing system. Upon entering this processing system,
the data are subjected to a detailed computer edit. Errors identified in this
phase are corrected and computer processing continues.
Two of the major steps of computer processing are the assignment of weights to
each sample person and imputation for missing survey responses. The weighting
procedures assure that SIPP estimates of the number of persons agree with
independent estimates of the population within specified age, race, and sex
categories. The procedures also assure close correspondence with monthly CPS
estimates of households. In almost all cases, a survey nonresponse is assigned
a value in the imputation phase of processing. The imputation for missing
responses is based on procedures generally referred to as the "hot deck"
approach. This approach assigns values for nonresponses from sample persons who
did provide responses and who have characteristics similar to those of the
nonrespondents.
The longitudinal design of SIPP dictates that all persons 15 years old and over
present as household members at the time of the first interview be part of the
survey throughout the entire 3 year period. To meet this goal, the survey
collects information useful in locating persons who move. In addition, field
procedures were established that allow for the transfer of sample cases between
regional offices. Persons moving within a 100-mile radius of an original
sampling area ( a county or group of counties) are followed and continue with
the normal personal interviews at 4-month intervals. Those moving to a new
residence that falls outside the 100-mile radius of any SIPP sampling area are
interviewed by telephone. The geographic areas defined by these rules contain
more than 95 percent of the U.S. population.
Because most types of analysis using SIPP data will be dependent not on data for
individuals but on groups of individuals (households, families, etc.) provisions
were made to interview all "new" persons living with original sample persons
(those interviewed in the first wave). These new sample persons entering the
survey through contact with original sample persons are considered as part of
he sample only while residing with the original sample person.
Go to Housing and Household Economic Statistics Division Home Page
Go to Census Bureau Home Page
Page Last Modified: March 09, 2001