Statistical Standards Program
Table of Contents
1. Development of Concepts and Methods
2. Planning and Design of Surveys
3. Collection of Data
3-1 Coverage for Frames and Samples
3-2 Achieving Acceptable Response Rates
3-3 Monitoring and Documenting Survey Contracts
3-4 Documenting a Survey System
4. Processing and Editing of Data
5. Analysis of Data / Production of Estimates or Projections
6. Establishment of Review Procedures
7. Dissemination of Data
For help viewing PDF files, please click here
|COLLECTION OF DATA|
SUBJECT: ACHIEVING ACCEPTABLE RESPONSE RATES
NCES STANDARD: 3-2
PURPOSE: To ensure that data collection programs conducted by or for the NCES are conducted in a manner that protects the rights of survey respondents to fair treatment and privacy, while at the same time encouraging high rates of response across all strata; since high response rates help ensure that results are representative of the target population.
GUIDELINE 3-2-A: The method of data collection (e.g., mail, telephone, Internet, etc.) should be appropriate for the target population and the objectives of the data collection.
GUIDELINE 3-2-B: The data should be collected at the most appropriate time of year.
GUIDELINE 3-2-C: The data collection period should be of adequate and reasonable length to achieve good response rates.
GUIDELINE 3-2-D: When appropriate, respondent incentives should be considered.
GUIDELINE 3-2-2A: The materials describing the data collection should be sent to respondents in advance, when possible.
GUIDELINE 3-2-2B: For interviewer administered data collection programs training should emphasize techniques for obtaining respondent cooperation and techniques for building rapport with respondents, including: respect for respondents' rights, manner, follow-up skills, knowledge of the goals and objectives of the data collection, and knowledge of the uses of the data.
GUIDELINE 3-2-2C: Prior to conducting a data collection program, endorsements, support, and the active cooperation of interested groups, such as professional organizations, professional associations, education community leaders, and state and local school district officials, should be obtained and communicated to respondents.
GUIDELINE 3-2-4A: The questionnaire should be pretested for the difficulty and interpretability of questions.
GUIDELINE 3-2-4B: The questionnaire should be pretested for ease in navigation of self-administered questionnaires.
GUIDELINE 3-2-4C: Questions should be clearly written and skip patterns easily followed.
GUIDELINE 3-2-4D: The questionnaire should be of reasonable length.
GUIDELINE 3-2-5A: Internal reporting systems that provide timely reporting of response rates and the reasons for nonresponse throughout the data collection should be developed. These systems should be flexible enough to identify important subgroups with low response rates for more intensive follow-ups.
GUIDELINE 3-2-5B: For longitudinal surveys, provide appropriate confidentiality assurances, while obtaining as much locating information about respondents as possible during initial contact (e.g., for a student, school address, home address, name of advisor, phone numbers of parents).
GUIDELINE 3-2-5C: If response rates are low after the initial phases of data collection, and if further data collection on the full sample is deemed too costly, take a random subsample of nonrespondents and use a more intensive data collection method. This subsample will permit a description of nonrespondents' characteristics, provide data needed for nonresponse bias analysis, and allow for possible weight adjustments or for imputation of missing characteristics.
GUIDELINE 3-2-5D: Determine a set of required response items to obtain when a respondent is unwilling to fully cooperate. These items may then be targeted in followup to meet the minimum standard for unit response. These items may also be used in a nonresponse bias analysis that compares characteristics of respondents and nonrespondents using the sample data for those items. These required response items may also be used for item nonresponse imputation systems.