Revised SS PartB

3

Supporting Statement

B. Collections of Information Employing Statistical Methods

1. Universe and Respondent Selection

The School Enrollment Supplement is collected as part of the October Current Population Survey (CPS), for which the universe is 105 million households and 300 million individuals. From the universe of 105 million households, we select a sample of which approximately 60,000 are eligible for interviewing. Interviews for the School Enrollment Supplement will be conducted with 55,000 households and 136,000 individuals in these households. The individual-level data represent the civilian, non-institutionalized population in the United States.

The additional questions about high school completion experiences will be asked about the 18- through 24-year olds in the outgoing sample rotations in October 2008. We expect that there will be approximately 3,000 18- through 24-year-olds in these outgoing rotations. Once interviews with the sampled 18- through 24-year-olds are completed, we will contact the high schools that they identified as the last high school they attended. We expect a response rate for the outgoing rotation cases of 90%, providing a sample of 2,700 cases for which the second stage high school contacts will be made. We expect a school-level response rate of approximately 90% as well. Given that there will be little clustering of outgoing rotation cases in terms of high schools attended and given a school-level response rate of 90%, we expect graduation information to be provided for approximately 2,430 outgoing rotation cases.

2. Procedures for Collecting Information

There will be additional items added to the end of the annual School Enrollment Supplement to the October CPS (see attachment A). Attachment D includes copies of letters that will be sent to school districts or schools identified during the CPS interview. We will call school districts associated with public schools identified by the respondent during the CPS interview to determine if the information request should be made to the district or to the school directly. This will determine if the school district or public school letter will be sent. Private schools identified during the CPS interview will be sent the private school information-request letter. Attachment B gives an overview of the CPS sample, design, weighting methodology, and response rates. The supplemental items will be administered for individuals in the outgoing sample rotations described in the attachment (rotations 4 and 8). The resulting sample size will allow detection of differences of 2 to 8 percentage points between estimates of the percentage of 18- through 24-year-olds with a regular diploma from the standard School Enrollment Supplement of the CPS and from the special study sample depending on race/ethnicity. The study was designed to look at all 18- through 24-year-olds in the civilian non-institutionalized population, and racial/ethnic subgroups in this population (White, non-Hispanics, Black, non-Hispanics, and Hispanics).

3. Methods to Maximize Response

Response rates and data accuracy for the CPS are maintained at high levels through computer edits, interviewer instruction and training, and close monitoring of the data collection. Refer to "Design and Methodology Current Population Survey Technical Paper 66” chapters 9, 15-16, and appendix D for a discussion of quality control activities for CPS (attachment B).

After the stage-one data collection work, Census will contact schools to obtain lists of graduates for 3-year periods centered on the year the stage-one respondent indicated having last attended the selected school. During this second stage data collection, Census will first call public school districts to determine the best person to contact to obtain graduation lists for the school, at either the school or the district. A letter will then be sent to this contact person for public schools, or to the school head for private schools, describing the study and requesting that graduation lists be mailed back to the Census Bureau using the prestamped envelope sent with the letter. Census telephone interviewers will then followup with the person if lists are not returned within 3 weeks. Further follow-up efforts will be utilized after 2 more weeks. The letter will contain a 1-800 number respondents can call if they have questions and a URL to a web site describing the study. Using similar methods for the Survey of School Crime and Safety, the Census Bureau obtained response rates near 80 percent. Given the very limited amount of information requested and limited effort needed to compile the information, we anticipate a response rate closer to 90 percent.

4. Tests of Procedures or Methods

Tests were conducted on the stage-one instrument and the stage-two letter. See attachments E and F for a summary of these tests.

5. Contacts for Statistical Aspects and Data Collection

The following individuals may be contacted on the statistical, data collection, and analysis operations:

Statistical Design:

Gregory Weyland

Demographic Surveys Division

U.S. Census Bureau

4600 Silver Hill Road

Washington, DC 20233

(301) 763-3790

Christopher Chapman

National Center for Education Statistics

U.S. Department of Education

1990 K St., NW

Washington, DC 20006

(202) 502-7414

Survey Content:

Kurt Bauman

Demographic Surveys Division

U.S. Census Bureau

4600 Silver Hill Road

Washington, DC 20233

(301) 763-6171

Steven Tourkin

Demographic Surveys Division

U.S. Census Bureau

4600 Silver Hill Road

Washington, DC 20233

(301) 763-3791

Christopher Chapman

National Center for Education Statistics

U.S. Department of Education

1990 K St., NW

Washington, DC 20006

(202) 502-7414

List of Attachments:

A—High School Completion Questionnaire

B—Overview of CPS Sample Design and Methodology

C—Source and Accuracy Statement

D—CPS School/District Letters

E—Cognitive Interview Research Report – stage-one tests

F—Cognitive Interview Research Report – stage-two tests

G—Federal Register comments