Support Stmt B_Suicide Prevention 2.0 Prog-Community Opinion Survey_updated Nov 2021

SUPPORTING STATEMENT B

Suicide Prevention 2.0 Program – Community Opinion Survey

OMB Control Number: 2900-NEW

B. COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS

1. Provide a numerical estimate of the potential respondent universe and describe any sampling or other respondent selection method to be used. Data on the number of entities (e.g., households or persons) in the universe and the corresponding sample are to be provided in tabular format for the universe as a whole and for each strata. Indicate expected response rates. If this has been conducted previously include actual response rates achieved.

The primary questions of interest focus on change at the community level in the measures of interest—for example, lowering of stigma levels, increased willingness to seek care, increased knowledge about Veterans and Veteran suicide. In order to examine these questions, communities will have to be surveyed at least twice, before new implementations of programs or policies, and after the implementation. The duration of the program or policy implementation will vary, which will affect the timing of the data collection cycles.

Individual respondents will not be re-surveyed, rather, two samples of the community will be taken at two time points to assess change at the community level. Data collection field periods will be chosen to coincide with the implementation schedule of the policy or program. In order to limit extraneous environmental influences, field periods will be a close as feasible to the implementation and will be compressed in time.

For this purpose, communities are typically defined to be individual States. Within the limit of 10,000 or fewer total completed cases per year, separate survey samples will be fielded in each of these several communities. The size of each community sample will be a function of the State population and the required statistical power. With these constraints, we estimate that there will be approximately 8 to 12 survey data collection cycles with final collected sample sizes varying between 830 and 1250.

The respondent universe are adults living in the community. The sample will be constructed based on an equal probability model of known households using high quality address-based sample lists. Stratified sampling will not be required. The initial samples will be constructed to be representative of the adult population of the State or relevant community with respect to age, gender, race, and ethnicity. The obtained final sample will be examined to identify any systematic non-response by demographic group, and the final data will be weighted to appropriately represent the survey community. This quantity will vary by community. The sample will be constructed based on an equal probability basis. Response rates will vary depending on location and the intensity of follow-up possible within the designated data collection field period but are expected to be consistent with rates generated by current best-practices in survey research.

2. Describe the procedures for the collection of information, including:

• Statistical methodology for stratification and sample selection

No stratification is anticipated at this time. The sample will be an Address-Based Sample (ABS) list obtained from Dynata (previously known as Survey Sampling Incorporated), which is recognized as an industry leader in statistically-sound survey research samples. These sample lists can be constructed using various filters, stratification designs, and oversampling parameters based on information at both the community level and the household level. However, we are specifying a simple random sample of households within the designated community. Sample records will contain street addresses as well as phone numbers and email addresses where available.

• Estimation procedure

The survey data will generate measures of proportions and percentages. The required sample sizes required to support analysis will be calculated based on expected variation in measures over time due to the impact of the interventions.

• Degree of accuracy needed

Standard alpha and beta levels.

• Unusual problems requiring specialized sampling procedures

None known.

• Any use of less frequent than annual data collection to reduce burden

For any given community, surveys might be able to be conducted more than a year apart if the implemented program or policy has a long implementation phase, or if the effects are not expected until more than a year after implementation

3. Describe methods to maximize response rate and to deal with issues of non-response. The accuracy and reliability of information collected must be shown to be adequate for intended uses. For collections based on sampling, a special justification must be provided for any collection that will not yield “reliable” data that can be generalized to the universe studied.

Survey response rates are a dual function of the ability to contact potential respondents and to engage their cooperation. Survey response rates will be maximized by using a high-quality initial sample combined with recruitment language focused on communicating the legitimacy of the research program, the saliency to the individual respondent, and the assurance of confidentiality. Survey respondents will be offered multiple modes of response and will be contacted repeatedly with reminders throughout the field data collection period. Despite intensive efforts, substantial levels of non-response are to be expected. Demographic characteristics of respondents will be compared with other sources of community-level data (e.g., Census data) as well as household profiles supplied by Dynata. Other tests for potential non-response bias can be conducted by comparing early respondents with later respondents. The final collected data will be weighted for non-response to correspond to the sampled community.

4. Describe any tests of procedures or methods to be undertaken. Testing is encouraged as an effective means of refining collections to minimize burden and improve utility. Tests must be approved if they call for answers to identical questions of 10 or more individuals.

All of the proposed survey items are taken from validated and reliable scales that have known psychometric properties and have been utilized in survey and other research in the past.

5. Provide the name and telephone number of individuals consulted on statistical aspects of the design and the name of the agency unit, contractor(s), grantee(s), or other person(s) who will actually collect and/or analyze the information for the agency.

Rani A. Hoff, 203-584-8344, is project lead and supervising data analyst and statistician for VA OMHSP personnel. Dr. Hoff is the Director of the Northeast Program Evaluation Center within the Office of Mental Health and Suicide Prevention (11OMHSP), VACO, and is a trained epidemiologist and statistician. Various OMHSP staff will contribute to the statistical analyses of data. Titan Alpha is the project prime contractor and will administer the survey and collect survey data from respondents.

Page 1