2011 ReSIPP Section B - Final

SUPPORTING STATEMENT

U.S. Department of Commerce

U.S. Census Bureau

2011 Re-engineered Field Test of the Survey of Income & Program Participation

B. Collection of Information Employing Statistical Methods

1. Universe and Respondent Selection

The SIPP respondent universe is the civilian noninstitutionalized population based on the 2000 decennial census, which contains approximately 270 million individuals. The SIPP uses a multistage stratified sample of the U.S. civilian noninstitutionalized population. The first stage involves the definition and division of the United States into groups of counties called the Primary Sampling Units (PSU), which are assembled into homogeneous groups called strata. The second stage involves selection of units within the PSU.

The 2011 Re-engineered SIPP Field Test sample is the fourth sample for the SIPP to be fielded from the 2000 redesign of the sample. There are 351 PSUs in the 2000 redesigned SIPP and in sample for the 2011 Field Test. The selected PSUs in the 2000 SIPP sample design cover both urban and rural areas of the United States and many were also in the 1990 SIPP sample design. PSU definitions, address lists, and area segments are all based on the 2000 decennial census.

Within each PSU living quarters (LQ) are systematically selected from lists of addresses prepared for the 2000 decennial census. Other sampling techniques are used to represent new construction, group quarters, and areas where incomplete addresses are common. Low income households were over sampled from the lists of addresses prepared for the census and from the lists of incomplete addresses. Were are taking sample from the 2000 redesign sample from the following states: CT, MA, NY, RI, MD, IL, WI, LA, TX, and CA. Basically, we are taking all the unit frame sample we have selected for SIPP from the high poverty stratum in self representing PSUs in two sample designations. The 2011 Re-engineered SIPP Field Test sample will consist of approximately 4,000 designated LQs, of which approximately 3,300 will be occupied at the time of interview and about 2,600 will be interviewed. Each household contains an average of 2.1 eligible respondents; therefore, 2011 Re-engineered SIPP Field Test should contain approximately 5,500 survey respondents. The expected response rate for this test is 75-80%. The 2010 Reengineered SIPP response rate was 81.85%.

2. Procedures for Collecting Information

In sample households, all people 15 years old and over will be interviewed using regular proxy-respondent rules as described in Attachment H. The interviewing period of the 2011 Re-engineered SIPP Field Test is as follows:

January 2011 to April 2011

We expect to obtain approximately 5,500 respondent interviews in the 2011 Re-engineered SIPP Test. The estimated total burden hours is 5,681 (includes recontact experiment).The 2011 Re-engineered SIPP Field Test will be conducted in all 12 Census Regional Offices from January 2011 to April 2011. Approximately 4,000 households are selected for the 2011 Re-engineered SIPP, of which, approximately 2,600 households are expected to be interviewed. We estimate that each household contains 2.1 people aged 15 and above, yielding approximately 5,500 person-level interviews in the field test. Interviews take one hour on average. The total annual burden for the 2011 Re-engineered SIPP interviews (includes recontact experiment) will be 5,681¹ hours in FY 2011. We expect the minimum detectable differences between the 2011 Field Test and the 2008 SIPP monthly participation rates to be approximately 0.7 for TANF and SSI, 1.6 for Food Stamps and WIC, and 1.8 for Medicaid at the 10% level of significance.

Recontact Experiment

As part of the transition from three interviews per year to one interview per year, new methods need to be tested for how to stay in contact with respondents so they can be located for the following year’s interview. Once interviews are completed in the 2011 SIPP field test we will conduct the Recontact Experiment. The objectives of the experiment are: 1) to test how a change of address form (Attachment F) mailed with or without a small monetary incentive or no contact between interview periods, effect attrition and the ability to locate respondents in the second wave of interviewing (Type A and Type D wave 2 non-response), and 2) to develop address update procedures which will facilitate locating original sample members who may have moved, and which can be implemented prior to and during the next interview field period.

During the recontact experiment we will have two treatment groups and a control group. Both treatment groups will receive a letter of explanation with the change of address form (see Attachment F). One of the treatment groups will receive an unconditional $5 incentive debit card. The SIPP-2011DR106(L) letter, Attachment D, will be mailed to this subset of cases, and the SIPP-2011DR107(L) letter, Attachment E, will be mailed to the treatment group that will not receive a monetary incentive. Households in these two treatment groups will receive a reminder letter along with a form, a few weeks later, if they did not respond to the first mailing. The control group will not receive any mailing. See Table 1 below for an illustration of the Recontact Experiment design.

Table 1. Study Design and Sample Size for the Recontact Experiment

Group	Cover Letter & Change of Address Form	Unconditional Incentive ($5 debit card)	Sample Size (Total estimated interviewed households = 2,600)	Estimated Number of Movers (based on ~25% poverty strata mover rate)
Treatment Group 1	Yes Attachment D & F	Yes	~ 870	~ 217
Treatment Group 2	Yes Attachment E & F	No	~ 870	~ 217
Control Group	No letter or form	No	~870	~ 217
	Total mailing ~ 1,740	Total with incentive ~ 870	~ 2,600	Total Movers ~ 650

Recontact Experiment Analysis

We will compare Type A (household non-interviews where occupants have not moved) and Type D (household non-interviews where the household has moved and are not able to be located) rates between treatment groups and expect to have minimum detectable difference of approximately:

• 1.7 and 1.2 (in Type A and Type D rates respectively) comparing those sent a change of address form and the control group; and

• 2.0 and 1.3 (in Type A and Type D rates respectively) comparing those sent a change of address form with the $5 incentive to those sent a change of address form with no monetary incentive.

3. Methods to Maximize Response

In all SIPP Panels we make special efforts to minimize non-interviews. In each wave, every household in the active sample receives an advance letter that explains the purpose of the survey and why their cooperation is important. In the 2011 Re-engineered SIPP Field Test each household will be given a brochure

(Attachment G) that contains information about the SIPP and informs respondents about the Census Bureau and our commitment to confidentiality. For Type A refusal households, standard procedures include additional visits to the household by another Field Representative (FR) or if needed, a Supervisory Field Representative (SFR) to convert the household response.

During the 1996, 2001, and 2008 SIPP Panels the Census Bureau experimented with giving monetary incentives to households in order to assess the effect on response rates and data quality. The Census Bureau’s plans are to use incentives to examine the effectiveness of an incentive on the response rate for the change of address form.

4. Tests of Procedures

The current 2011 Re-engineered SIPP Field Test is part of a program of evaluation and development emerging from a comprehensive reassessment of the SIPP. The Re-Engineered SIPP is an evolving process and will have multiple developmental and testing stages. The 2011 Re-engineered SIPP Field Test as outlined above will test the full implementation of the Re-engineered SIPP. These developmental stages are interspersed by a series of smaller, specifically focused content, instrument, and systems tests.

5. Contacts for Statistical Aspects and Data Collection

The Census Bureau will collect and process these data. Within the Census Bureau, the following individuals should be consulted for further information on their areas of expertise:

Sample Design

Tracy Mattingly Chief, SIPP Branch

Demographic Statistical Methods Division

301-763-6445

Data Content

David Johnson Chief, Housing and Household Economic Statistics Division

301-763-6443

Data Collection and Tabulation

Patrick Benton Chief, Income Surveys Branch

Demographic Surveys Division

301-763-4618

Attachments

A. 2011 Re-engineered SIPP Items Booklet

B. SIPP-105(L)DR(2011)–Director's Letter

C. SIPP-105(L)(SP)DR(2011)–Director's Letter Spanish Version

D. SIPP-2011DR106(L)–Change of Address Letter with incentive

E. SIPP-2011DR107(L)–Change of Address Letter without incentive

F. 2011 Change of Address Form

G. SIPP-4006A Brochure “SIPP You Represent Your Nation”

H. Respondent Rules

1¹See page 9 of Part A for table on burden hours.