omb supporting statement part b.wpd

SUPPORTING STATEMENT

U.S. Department of Commerce

U.S. Census Bureau

Survey of Health Insurance and Program Participation (SHIPP)

OMB Control Number 0607-<XXXX>

Part B – Collections of Information Employing Statistical Methods

Question 1. Universe and Respondent Selection

Two types of sample will be used: random digit dial (RDD), with a goal of 3,000 completed interviews, and "seeded" sample of known Medicare enrollees from the Centers for Medicare and Medicaid Services (CMS), with a goal of 2,000 completed interviews. The RDD sample will be screened through “ID Plus” to reduce the number of invalid and ineligible phone numbers. The CMS sample has been screened to delete records that do not have an enrollment start date, records that do have a termination date, and persons who are deceased or for whom English is not their primary language.

For the RDD sample there will be no stratification. Phone numbers will be screened and if they are associated with a household, the interviewer will attempt to identify a household member 18 years old or older to conduct the survey. If this attempt fails they will attempt to find a household member 16 or 17 years old to participate. A single household respondent will be asked questions about all household members.

The CMS data will be stratified on age and date of enrollment. Specifically, those under 65 and those enrolled at some point after January 1, 2009, will be selected at a higher rate. Since the majority of Medicare enrollees receive the coverage automatically when they turn 65, and the senior citizen community is by and large aware of this program, those 65 years old and older, and those enrolled for a number of years are likely not to be confused about their coverage. However, those under 65 most likely have the coverage due to a disability, and may be more susceptible to confusing the program with Medicaid. Regarding time period, those who are more recently enrolled may have more difficulty accurately reporting their coverage than those enrolled for several years. The rationale for increasing the proportion of these types of respondents is to test the relative strengths of the three questionnaires in deriving accurate reporting under less-than-ideal circumstances. Furthermore, the fact that CMS data contains specific date of enrollment data enables a rich analysis of the accuracy of reporting the timing and duration of coverage. That is, it will be possible to assess not just coverage “at any time” during the calendar year, but also whether the respondent accurately reported start dates and specific months of coverage. See Table 2 for details on sample distribution.

With regard to response rates, we are estimating something in range of 50%. The most recent large-scale split-ballot survey conducted by the Census Bureau (in 2006) resulted in a response rate of 59% (using the AAPOR RR6 definition). The climate for RDD surveys has only deteriorated since then, but one mitigating factor is the subject matter. We expect that given the attention health reform has received in recent months, respondents may be somewhat more positively inclined to participate in the survey.

Table 2: Distribution of CMS Sample: Completed Interviews

		Age
		Under 65	Over 65	TOTAL
Enroll Date	Before Jan. 1, 2009	360 (120/panel)	240 (80/panel)	600 (200/panel)
	After Jan. 1, 2009	840 (280/panel)	560 (187/panel)	1,400 (467/panel)
	TOTAL	1,200 (400/panel)	800 (267/panel)	2,000 (667/panel)

Question 2. Procedures for Collecting Information

All interviews will be conducted by telephone interviewers at the Census Bureau’s telephone facility in Hagerstown, Md. In order to minimize interviewer effects, interviewers will be randomly assigned to one of three groups (1, 2 and 3), and each interviewer group will work on all three questionnaire versions (CPS, ACS and Redesign) over the course of the entire field period. In order to allow each questionnaire version “equal access” to fresh sample and fresh interviewers, the field period will be divided into three time periods of two weeks each, and within each time period all three questionnaire versions will be worked evenly.

Interviewer groups will first be randomly assigned to one questionnaire version, and they will work on only that version during the first time period (Weeks 1-2). At the end of Week 2, each interviewer group will be rotated off of that first questionnaire version and on to a different questionnaire version. They will receive a brief training on the new questionnaire version, focusing just on the differences between their previous questionnaire and the new one. They will then work on just that second questionnaire version throughout the second time period (Weeks 3-4). At the end of Week 4 interviewers will again be rotated to their third and final questionnaire version and receive a brief training on the new version, and during the last time period (Weeks 5-6) they will work on only that version. Over the course of the survey, the interviewers will work in all 3 time periods and all 3 questionnaire treatments. In any given time period, an interviewer will be working on a single questionnaire treatment. The field period will run from March 22 through May 10, 2010.

In order to accommodate this type of rotation there will be nine independent samples – one for each unique combination of interviewer group/questionnaire version/time period. For example, Interviewer Group 1 will be assigned to work on CPS during Weeks 1-2. At the end of Week 2, that particular sample will be closed out for good. Interviewer Group 1 will then move on to the ACS questionnaire and a new sample will be released for them to work on that version during Weeks 3-4. At the end of Week 4 this sample will be closed out for good and Interviewer Group 1 will move on the EXP questionnaire and another new sample will be released for them to work on that version during Weeks 5-6. This same routine will be repeated for Interviewer Groups 2 and 3, for a total of 9 independent samples.

Question 3. Methods to Maximize Response

All interviewers working on the SHIPP survey will have had several years of experience in working on RDD surveys, and thus will have some familiarity with and skills at cold-calling respondents and persuading them to participate in a survey. In addition to this general experience, interviewers will be trained in the content and purpose of the SHIPP survey, and they will be given a set of responses to address common objections from respondents. The Hagerstown telephone facility also has specially-trained refusal conversion interviewers who will be assigned to the SHIPP project.

The initial parameters in the call scheduler are set at a maximum of 20 calls per case. However, this can be modified during data collection within any given phase, and at the end of a phase a more complete analysis can be conducted in order to adjust the parameters for the subsequent phase. We have also drawn extra sample to hold in reserve. If at about the half-way mark of a given field period it appears that we are at risk of missing our target number of completed interviews we may release more sample, balancing the need for a target number of completes with upholding a reasonable response rate.

Question 4. Tests of Procedures or Methods

As noted above, the SHIPP Redesign instrument has been developed following extensive testing. Based on an ongoing review of the literature, iterative cognitive testing, and a series of split-ballot field tests, a preliminary Redesign was developed for cognitive testing in the spring of 2008. Adjustments to the questionnaire we made and a pretest was conducted in March 2009. The CPS and ACS health insurance questions have also gone through cognitive testing. See Part A, Question 8 for a partial list of relevant documentation.

Question 5. Contacts for Statistical Aspects and Data Collection

Several individuals will be involved in the statistical analysis, including:

1. Joanne Pascale, Statistical Research Division (301-763-4920)

2. Amy Steinweg, Housing and Household Economic Statistics Division (301-763-3834)

3. Steve Ash, Demographic, Demographic Statistical Methods Division (301-763-4294)

4. John Magruder, Telephone Center Coordinating Office (301-763-7789)

Attachments:

1. SHIPP questionnaire

2. SHIPP advance letter

3. SHIPP ACS & CPS state-specific plan names

4. SHIPP CPS state-specific plan names

5. TANF names