0615 2013 SS 102913 Part B rev

SUPPORTING STATEMENT

NOAA Engagement Survey Instrument

OMB CONTROL NO. 0648-0615

B. COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS

1. Describe (including a numerical estimate) the potential respondent universe and any sampling or other respondent selection method to be used. Data on the number of entities (e.g. establishments, State and local governmental units, households, or persons) in the universe and the corresponding sample are to be provided in tabular form. The tabulation must also include expected response rates for the collection as a whole. If the collection has been conducted before, provide the actual response rate achieved.

Potential respondents are constituent groups located within any of the coastal and Great Lakes states with Sea Grant Programs. There are 32 Sea Grant Programs. The survey will be implemented by NOAA Sea Grant Programs. The desired response rate is 25% based on a 5-40% range for customer surveys. The estimated sample size for the 7 constituent groups to be sampled is provided in Table 1. Each group represents a cross section of the groups with which Sea Grant works. The higher the estimated sample, the more variability we expect within each group.

The survey approval came within months of the Deepwater Horizon Oil Spill. As a result the necessary changes in job duties associated with responding to the spill, the survey was not administered; therefore we have no prior response rate.

Table 1. Seven Constituent Groups to be sampled: Estimated sample size and number of completed responses based on an estimated 25% response rate. The larger estimated samples indicate strata with larger populations.

Constituent Group	Estimated Sample	Estimated Number of Completed Surveys
Non-profit organizations	50	13
Other Federal Agencies	100	25
NOAA Partners	150	37
State and local governments	200	50
K-12 Education Professionals	200	50
Higher Education Professionals	200	50
Business and Industry	400	100
Total	1,300	325
Expected response rate	25%

2. Describe the procedures for the collection, including: the statistical methodology for stratification and sample selection; the estimation procedure; the degree of accuracy needed for the purpose described in the justification; any unusual problems requiring specialized sampling procedures; and any use of periodic (less frequent than annual) data collection cycles to reduce burden.

Since the sample population is divided into seven subgroups (see Question 1 above) that are more homogeneous as individual groups than as a whole population, we will use the seven strata identified in Part B, Question 1. Simple random sampling will then be used to obtain the expected sample size within each stratum. By using a stratified random sampling scheme we

will be able to develop a weighted mean for strata with larger populations with which Sea Grant engages the most.

Email addresses will be collected over a period of 90 days. The email list will be drawn from databases maintained by individual Sea Grant programs and consists of constituents who previously used Sea Grant products or services. The survey instrument will be emailed to members in the subgroups identified in Question 1 above using a stratified sampling technique. As noted in the table above, more samples will be taken in subgroups that have more potential respondents (larger population).

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

We will send an email a few days prior to distributing the survey and inform the participant that they will receive the engagement survey shortly. The participant will receive the survey two to three days later. Three weeks later we will follow-up with an email thanking those who have completed the survey and ask non-respondents a final time to take the survey.

We will compare the types of constituent and demographic information of respondents and nonrespondents. If we observe a potential non-response bias, we will weight the responses accordingly.

The survey questions were developed using primarily a five-point Likert scale instead of open ended questions to maximize the response rate.

A workshop which included a panel of experts in social sciences was held with multiple follow-up conference calls to generate survey questions tailored to determine how well NOAA engages with constituents. This panel of experts addressed threats to content validity by developing a list of questions that when answered match outcomes and conditions identified in a table of specifications. The survey instrument was piloted with 9 non-NOAA constituents to determine question reliability and ease of use. A 0.8 Cronbach alpha for question reliability will be considered acceptable.

4. Describe any tests of procedures or methods to be undertaken. Tests are encouraged as effective means to refine collections, but if ten or more test respondents are involved OMB must give prior approval.

The survey was piloted by 9 non-federal employees serving on a NOAA Gulf of Mexico Regional Collaboration Team Engagement Working Group to check for functionality of survey instrument, ease of use and internal reliability. Based on feedback from the pilot respondents, minor revisions were made to the survey.

5. Provide the name and telephone number of individuals consulted on the 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.

Statistical methods and data analysis: LaDon Swann, Ph.D. (251) 64-5877 or [email protected].

Survey administration; Sami Grimes , (301) 734-1073 or [email protected].

4