The Survey of Income and Program Participation (SIPP) is a household-based survey designed as a continuous series of national panels. Each panel generally features a large sample of households that are interviewed multiple times over a four-year period. SIPP data provide the most comprehensive information available on how the nation’s economic well-being changes over time, which has been SIPP’s defining characteristic since its inception in 1983.

Sponsoring agency: US Census Bureau

Data universe:

The SIPP sample is a multistage-stratified sample of the U.S. civilian non-institutionalized population.

Disaggregated Asian and Native Hawaiian or Other Pacific Islander categories collected:

Are disaggregated Asian and Native Hawaiian or Other Pacific Islander data publicly available? NO

Measures available:

Sample size and unit of analysis:

The SIPP survey design is a continuous series of national panels, with sample size ranging from approximately 14,000 to 52,000 interviewed households. The duration of each panel ranges from 2 ½ years to 4 years. The SIPP sample is a multistage-stratified sample of the U.S. civilian non-institutionalized population.

Types of geography available to researchers: National, region, state, metro/nonmetro

What data are available?

What is the difference between PUBLIC-USE and RESTRICTED-USE data files:

PUBLIC-USE data include top- and bottom-coded values, and some data are suppressed due to small cell size. RESTRICTED-USE data include all collected data.

How to access the PUBLIC-USE data:

1. Go to census.gov
2. Select the "Surveys & Programs" tab, and select "Survey of Income and Program Participation (SIPP)" from the drop-down.
3. Next select "Data" from the left-hand navigation bar: https://www.census.gov/programs-surveys/sipp/data.html

How to obtain permission to use the RESTRICTED-USE data:

The Census Bureau considers proposals from qualified researchers in social science disciplines consistent with the subject matter of the surveys and censuses collected by the Census Bureau. Proposals may be submitted at any time.

1. Go to census.gov
2. Select "Surveys and Programs", and "All surveys and programs."
3. Select "Center for Economic Studies," and then navigate to "Data" (on the left side of the CES page).
4. Select "RESTRICTED-USE Data", and then "Apply for access": https://www.census.gov/about/adrm/ced/apply-for-access.html

Constraints surrounding access to RESTRICTED-USE data (e.g., citizenship requirements, cost, etc):

All researcher access to RESTRICTED-USE data occurs at secure Federal Statistical Research Data Centers (FSRDC). Some FSRDCs may charge fees for access to their facilities.

Agency policy re. sample sizes/publishable estimates/data suppression standards:

The Census Bureau recommends a minimum weighted estimate - i.e., the weighted totals of the sample cases included in the analysis - of 200,000 for computing cross-sectional estimates and 300,000 for computing longitudinal estimates. Nonsampling error in one or more of the small number of cases providing the estimation can also cause large relative error in that particular estimate. Care must be taken in the interpretation of small differences since even a small amount of nonsampling error can cause a borderline difference to appear significant or not, thus distorting a seemingly valid hypothesis test. https://www2.census.gov/programs-surveys/sipp/tech-documentation/source-accuracy-statements/2019/sipp-2019-SA-24-SEP21.pdf

Information on when the data were collected/what time period could be examined using the data:

The first SIPP panel, the 1984 Panel, began interviews in October 1983. The 1985 Panel began in February 1985. Subsequent panels began in February of each calendar year, resulting in concurrent administration of the survey in multiple panels. In several instances, due to budget and other issues, panels were terminated after seven interviews (28 months). Three panels were terminated even earlier: 1988 (six interviews), 1989 (three interviews), and 2000 (2 interviews). With certain exceptions, each panel overlapped part of the previous panel, with the result that there were two or three active panels at any given time. Overlapping panels allow data users to pool records from different panels, thus having larger samples (and lower standard errors) for cross-sectional analyses. The overlapping feature of the SIPP design was dropped for the 1996 through 2014 Panels, but standard errors for non-overlapping panels remained small since at least 29,000 households were interviewed (considerably more than in the previous panels). Similar to the 1990 through 1993 Panels, the 2018 Panels and beyond overlap with new panels that begin each subsequent year (2019, 2020, and so on).

Where to find disseminated official estimates:

1. Go to census.gov
2. Select the "Surveys & Programs" tab, and select "Survey of Income and Program Participation (SIPP)" from the drop-down.
3. Recent publications are currently listed at the bottom of the page. https://www.census.gov/programs-surveys/sipp.html

For older publications and table packages, select the "Library" tab on the left hand side of the page. https://www.census.gov/programs-surveys/sipp/library.html

Type of data (survey, program, admin etc.): Survey

Do the data include measures of citizenship, or are respondents limited by citizenship (i.e., only U.S. citizens are included in the data)?

Nativity and citizenship information were collected in the Migration topical module prior to the 2014 panel, and in the core survey in 2014 and beyond. There is no citizenship limitation on survey respondents residing in sampled households.

Analytic Considerations: NONE