Assessment Supporting Statement Part B

Part B
Statistical Methods

The CDFI Fund has contracted with Abt Associates to conduct a web-based survey of all CDFIs that have applied to the CDFI Fund for FA or TA awards or for certification, or have been surveyed as part of the CDP in the past three years. The total universe of such CDFIs is estimated to be approximately 1,100. Each CDFI will be requested to respond to survey modules relating to the specific types of CDFI Fund programs they applied for/participated in. No sampling is recommended because the number of CDFIs eligible to respond to each module is considerably lower than the total of 1,100.

B1 Potential Respondent Universe

The survey will include all CDFIs that have applied to the CDFI Fund for FA or TA awards or for certification, or have been surveyed as part of the CDP in the past three years.

A total of 862 CDFIS have been identified through the CDFI Fund sources and 238 additional CDFIs through the CDP, for a total of 1,100 CDFIs.

B2 Statistical Methods

B2.1 Sampling Plan

No sampling is needed, because the survey will include all identified CDFIs.

B2.2 Justification of Level of Accuracy

All CDFIs that have applied to the CDFI Fund for FA or TA awards or for certification, or have been surveyed as part of the CDP in the past three years will be surveyed in order to obtain comprehensive information on CDFI Fund programs. Based on our previous experience and the planned survey approach, we anticipate achieving a 75 percent response rate. In evaluating the results of the survey, we will assess the extent to which non-respondents differ from respondents to determine whether the findings are likely to be representative of all CDFIs. To the extent that there are significant differences between respondents and non-respondents, we will note these differences in our presentation of the findings and, if feasible, attempt to incorporate statistical adjustments to the survey results.

B3 Maximizing Response Rates

The survey is planned as a web-based survey with telephone follow-up. The survey will be addressed to the same person who completed the CDFI Fund annual survey to ensure that the appropriate person receives the survey. The survey will allow the respondent to refer to other staff or files for answers to any questions that they cannot address from memory. Extensive e-mail and telephone follow-up will be used to ensure that the appropriate party received the survey and to encourage respondents to reply. To ensure a high response rate, we will also pursue completion of the survey over the telephone when appropriate. In such cases, completion of the survey may require more than one telephone call to allow the respondent time to prepare answers, such as those involving quantitative data. As noted in Section B2, we anticipate achieving a 75 percent response rate.

B4 Tests of Procedures or Methods

Early drafts of the instrument have been reviewed by several outside consultants in order to ensure that the instrument is clear, flows well, and is as concise as possible. In addition, each module of the instrument as submitted in this package will be tested in January 2006 with up to nine respondents.

B5 Statistical Consultation and Information Collection Agents

The CDFI Fund has contracted with Abt Associates, Inc. to conduct the data collection. The data collection procedures will be similar to those used in other surveys conducted by Abt Associates.