0704-rand_ssb_7.12.21

SUPPORTING STATEMENT – PART B

B.  COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS

If the collection of information employs statistical methods, it should be indicated in Item 17 of OMB Form 83-I, and the following information should be provided in this Supporting Statement:

1.  Description of the Activity

Describe the potential respondent universe and any sampling or other method used to select respondents.  Data on the number of entities covered in the collection should be provided in tabular form for the universe as a whole and for each of the strata in the proposed sample.  Indicate the expected response rates for the collection as a whole, as well as the actual response rates achieved during the last collection, if previously conducted.

The activity includes interviewing high schools/LEAs. The study will be concentrated in four states including California, Pennsylvania, Ohio, and Florida.

Study States	Potential High Schools	Sample High Schools	Number of Interviews Per School (for each sample school)
CA	1529	6	1 Principal/Vice Principal 1 Counselor 2 District Personnel
FL	586	6	1 Principal/Vice Principal 1 Counselor 2 District Personnel
OH	869	6	1 Principal/Vice Principal 1 Counselor 2 District Personnel
PA	656	6	1 Principal/Vice Principal 1 Counselor 2 District Personnel

• We will select six pairs of public high schools in each state. Each pair will include two high schools that are similar in demographics, but one provided full access to recruiters while the other provided either no or limited access.

• The study will interview school district (LEA) administrators overseeing recruiter access at the high schools, high school administrators (either principal or vice principal) and high school counselors.

In each state we identified a large number of high schools (see table above). Only 24 (6 in each state) will be selected for the study. Thus, we expect we will achieve our sample size.

In terms of the respondents, they are pre-defined. Within the 24 schools that indicate their willingness to participate we will interview principals/vice principals and high school counselor at the school level and district administrators who oversee recruiter access. We expect 90% response rate from interviewees. There are no previous data collection efforts and thus there are no previous response rates.

2.  Procedures for the Collection of Information

Describe any of the following if they are used in the collection of information:

1. Statistical methodologies for stratification and sample selection;

To identify the states and the high schools that would be eligible to include in our sample for qualitative interviewing, we merged a number of datasets and conducted a series of propensity score procedures, namely nearest neighborhood matching methods. RAND first analyzed the recruiter access dataset (produced JAMRS) provided by the Accession Policy. This dataset listed all high schools that were non-compliant or had limited recruiter access. RAND identified states that have large numbers of non-complying schools in different geographic parts of the United States. The states are: California, Pennsylvania, Ohio and Florida. RAND then merged the non- compliant school dataset with the datasets from the Department of Education and the American Community Survey and state websites. The merged datasets provided demographic, neighborhood, and graduation information on all complying and non-compliant schools in each of the four state. Within each state, we first identified cities that have large number of compliant and non-compliant schools. Then we applied near neighborhood matching methods to each of the large cities to identify schools whose characteristics are similar but vary on whether they allow recruiters to access the school/provide list. The schools were matched on: neighborhood characteristics (poverty level, percent veterans, percent active in the military, percent unemployed, voting pattern) and school characteristics (graduation rate, percent of free/reduced lunch, student demographic characteristics). For cities that did not have large number of schools we conducted nearest neighbor matching method across the state.

We then identified a list of paired schools in each state. RAND will contact the schools on the identified list until the sample size of 24 high schools are achieved.

b.  Estimation procedures;

Does not apply, since RAND will be collecting qualitative data on the high schools (and corresponding school district) that agree to participate

c.  Degree of accuracy needed for the Purpose discussed in the justification;

Does not apply, since RAND will be collecting qualitative data on the high schools (and corresponding school district) that agree to participate.

2. Unusual problems requiring specialized sampling procedures; and

Does not apply.

e.  Use of periodic or cyclical data collections to reduce respondent burden.

Does not apply.

3.  Maximization of Response Rates, Non-response, and Reliability

Discuss methods used to maximize response rates and to deal with instances of non-response.  Describe any techniques used to ensure the accuracy and reliability of responses is adequate for intended purposes.  Additionally, if the collection is based on sampling, ensure that the data can be generalized to the universe under study.  If not, provide special justification.

The number of schools that are eligible to participate is large. Schools will be contacted until 24 high schools agree to participate. Given the large sampling frame the study is likely to achieve its sample size.

RAND will use structured interview protocols to ensure that all issues relevant to the study are addressed. RAND during the interviews will also use follow up questions to validate the interview responses.

The collection is not based on random sampling; thus generalizability is not applicable to this study.

4.  Tests of Procedures

Describe any tests of procedures or methods to be undertaken.  Testing of potential respondents (9 or fewer) is encouraged as a means of refining proposed collections to reduce respondent burden, as well as to improve the collection instrument utility.  These tests check for internal consistency and the effectiveness of previous similar collection activities.

RAND will test the protocols during the first school interview and will refine the instrument accordingly to increase reliability and validity.

5.  Statistical Consultation and Information Analysis

a. Provide names and telephone number of individual(s) consulted on statistical aspects of the design.

The design is not statistical in nature. It is a qualitative piece. Team members have both expertise in qualitative and quantitative methods.

b. Provide name and organization of person(s) who will actually collect and analyze the collected information.

RAND researchers will collect and analyze the data. They include: Rita Karam, Nelson Lim, Kim Hall, and Monica Rico.

All team members are from the RAND Corporation.

Below is the contact information for the PIs.

Dr. Rita Karam – Senior Policy Researcher, 1776 Main Street, Santa Monica, CA (310)393-0411/ ext. 6537

Dr. Kimberly Hall – Senior policy Researcher, 1200 South Hayes Street, Arlington, VA 22202-5050, (703) 413-1100, ext. 5325

2