Supporting Statement Part B

Subsidized and Transitional Employment Demonstration and Evaluation Project (STEDEP)

Supporting Statement for OMB Clearance Request

Part B: Statistical Methods

June 2010

B1. Respondent Universe and Sampling Methods

Respondents will be identified through several means. Literature reviews and existing studies will be consulted (and, where necessary, additional review will be conducted) to assess what is currently known about STEDEP. Members of constituent groups (e.g. American Public Human Services Association, National Association for Welfare Research and Statistics) and national organizations (e.g. National Transitional Jobs Network) will be important stakeholders from the practitioner and policy communities. Finally, we will use a “snowball” sampling technique that relies on referrals from initial respondents, to generate additional respondents. Thus, we anticipate that stakeholders identified either through the literature or national organizations will recommend other individuals with whom we should conduct interviews.

B2. Procedures for Collection of Information

Informal discussions with stakeholders will be conducted by telephone and in-person. Discussions will be conducted commencing with the receipt of OMB clearance or award of the STEDEP contract (expected September 30, 2010), whichever comes later, and will occur most heavily in the first year of the contract but may extend into the second year. Discussions will be conducted by senior members of the selected evaluation contractor.

Contractor staff will contact potential discussants and obtain their consent to setting up an appointment for a telephone or in-person discussion. Contractor staff will use the approved instruments to guide the discussion and help ensure that appropriate topics are covered, given the type of stakeholder being interviewed. Contractor staff will take notes during the discussion, obtain relevant written materials that are readily available, and prepare written summaries of each discussion and group of discussions for submission to ACF.

We anticipate that the discussions will vary depending on the respondent and that not more than 250 respondents will be interviewed over two years (i.e. 125 respondents per year).

Exhibit B2.1 Estimated Response Time
Instrument	Number of Respondents over Two Years	Average Burden Hours Per Response
Discussion Guide for Use with Researchers, Policy Experts, and Coordinators	100	1
Discussion Guide for Use with Program Directors	50	2.5
Discussion Guide for Use with Program Staff	100	2
Total	250	-

B3. Methods to Maximize Response Rates and Deal with Nonresponse

We expect to obtain a very high response rate (95 percent) among stakeholders who will be interviewed. Several factors will help ensure a high rate of cooperation among respondents. First, senior staff members of the study team who are familiar with the issues will conduct the discussions. Second, it is expected that staff conducting the discussions will personally know many of the respondents through their professional connections. Finally, the stakeholders who will be interviewed are all heavily invested in the issues surrounding pregnancy prevention and thus will be interested in contributing to the development of the interventions to be tested in the study.

B4. Tests of Procedures or Methods to be Undertaken

As discussed in Section A12, the discussion guides are similar to discussion protocols that have been used successfully in prior studies.

B5. Individuals Consulted on Statistical Aspects and Individuals Collecting and/or Analyzing Data

The information will be collected by the contractor selected to conduct the STEDEP evaluation, and its subcontractors, on behalf of the US Department of Health and Human Services (HHS), Administration for Children and Families (ACF). With ACF oversight and approval, the contractor will be responsible for the finalizing the study design, data collection, analysis, and report preparation. Key input to the current data collection instruments was received from the following individuals:

Department of Health and Human Services

Administration for Children and Families

Office of Planning, Research, and Evaluation

• Girley Wright, Senior Program Analyst

• Mark Fucello, Division Director

• Naomi Goldstein, Director

Inquiries regarding statistical aspects of the study design should be directed to:

Girley Wright

Office of Planning, Research, and Evaluation

Administration for Children and Families

U.S. Department of Health and Human Services

370 L'Enfant Promenade, S.W.

Washington, DC 20477

202-401-5070

Ms. Wright is the project officer and has overseen the design of the data collection instruments.