NPA SS 121207 Part B

SUPPORTING STATEMENT
NOAA AWARENESS STUDY
OMB CONTROL NO.: 0648-xxxx

B. COLLECTION OF INFORMATION EMPLOYING STATISTICAL METHODS
1. Describe (including a numerical estimate) the potential universe and any sampling or other
respondent selection methods to be used. Data on the number of entities in the universe
covered by the collection and in the corresponding sample are to be provided in tabular form
for the universe as a whole and for each of the strata in the proposed sample. Indicate
expected response rates for the collection as a whole. If the collection has been conducted
previously, include the actual response rate achieved during the last collection.
The potential respondent universe is the total population of the U.S who currently has internet
access. There are, according to a 2006 nation-wide Harris Interactive study, approximately 172
million Americans online. The research sample will be purchased from one of many firms
specializing in extracting online email records, such as American Business Information, Donnelley
Marketing/American Consumer Lists, Hugo Dunhill Mailing Lists, and Experian. Hard censusbased quotas will be set so that our collective pool is reflective of a convenience sample of the
broader U.S. population, but note, it will not be representative.
After reviewing refusal rates across hundreds of Kelton Research studies, online statistics, and
other available research data, the research firm finds that refusal rates for marketing research
studies typically run between 20%-50% depending on the nature and timing of the project. We will
continue the interview process until we have the required number of interviews. All interview
attempts will be among individuals within the specifications for that given phase.
In order to find the most articulate and insightful respondents for the qualitative component, the
research firm uses its proprietary StreetSmart research team to recruit respondents online, via
telephone and in-person. It uses tiered recruit screening criteria to ensure the most accurate,
reliable and knowledgeable participants. Respondents are selected to participate based on multiple
demographic and psycho-graphic criteria. For NOAA, this would include, but not be limited to:
age, gender, income, interest in earth sciences, and self-reported knowledge of earth science
related issues. The sample will not be representative of the target audiences.
Respondents for the Focus Groups are sent lobby exercises prior to each session to further test for
quality and ensure we interview a pool of articulate and engaged participants. The research firm’s
principals speak with every focus group participant on check-in to confirm their information is
correct and make sure they are representing themselves accurately. Participants are paid $50.

2. Describe the procedures for the collection of information including: a. Statistical
methodology for stratification and sample selection, b. Estimation procedures, c. Degree of
accuracy needed for the purpose described in the justification, d. Unusual problems requiring
specialized sampling procedures, and any use of periodic (less frequent than annual) data
collection cycles to reduce burdens.
Proprietary emailing software is used to invite each survey respondent to participate in the study.
Respondents will be selected using screening criteria at the beginning of each survey to ensure that
we are only interviewing the correct respondent types for each subgroup. Hard quotas are
programmed into the online survey logic to ensure that respondent data reflects available U.S.
census information for each relevant audience. Completion times are monitored to ensure that each
respondent is accurately taking the study and not simply clicking through to the end.
Upon completion, all data is collected into a proprietary database system where results are processed
and monitored. All fieldwork, processing, and analysis of results are conducted internally to ensure
complete data integrity and security. The research firm employs a variety of analytical tools in each
deliverable, including but not limited to drivers analysis, correlation and regression analysis, ttesting, and cross-tabular analysis.
The research firm does not anticipate any unusual problems requiring specialized sampling
procedures nor the use of any periodic data collection cycles to reduce burdens.
3. Describe methods to maximize response rates 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.
Respondents are immediately notified that the online survey is for a national market research study
on current social issues in our society, and that they will remain anonymous and not be held
accountable for their views. They are additionally assured that they are not being solicited to try or
use any product or service.
Surveys are distributed electronically from a secure central location. Distribution is computerized, so
that all contacts are automatically verified and classified. Additionally, supervisory personnel are
monitoring electronic responses for validation and other aspects of quality control.
Multiple respondents can connect simultaneously to the online survey, and any respondents who are
unwilling to participate or do not qualify for the survey are automatically thanked for their time and
opinions and then terminated.
Non-respondents will be sent two reminder emails informing them that the survey is still ongoing
and that their feedback is still desired. Because the survey is relatively brief and has been carefully
designed using input from qualitative sessions and pre-survey testing of our key audience groups,
respondent fatigue is minimized.

This collection is not based on sampling, other than convenience sampling reflective of different
segments of the public, and we are making no claims that the results can be generalized to the
public.
4. Describe any tests or procedures or methods to be undertaken. Testing is encouraged as
an effective means of refining collections of information to minimize burden and improve
utility. Tests must be approved if they call for answers to identical questions from 10 or
more respondents. A proposed test or set of tests may be submitted for approval separately
or in combination with the main collection of information.
Detailed survey designing software ensures that all appropriate questions are asked, and that any
skip patterns are followed. The online surveys are carefully crafted and tested to ensure that
administration is consistent from interview to interview. Any interview found for any reason not to
be completed to standards will be terminated and replaced by another suitable respondent with
identical demographic characteristics.
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.
Paul Bragan (Kelton Research), 202-487-4896, Dr. Larry Percy (Harmonic International), 334-2650094