National Election Studies Study Implementation

There are three main stages in the implementation of each NES study: drawing the sample; conducting the interviews; and preparing the data and documentation for dissemination. The first two stages comprise a joint effort between the NES Project Staff and various units of the Survey Operations Unit of the Survey Research Center of the Institute of Social Research. For the last stage, NES staff is responsible for carefully reviewing and processing the data for public release after interviewing is complete, and NES standards for data accuracy are high while every effort is made to have the data available to the user community as soon as possible.

Samples for the NES Time-Series Data Collections

Following the specifications provided by the NES Project Staff, the Survey Research Center Sampling Section draws our national face-to-face samples from their National Sample. The sample universe is traditionally all U.S. households (including civilian households on military bases) in the 48 coterminous states and the District of Columbia.

As an example, the 1990 SRC National Sample, like its predecessors based on the most recent decennial census, is a multi-stage area probability design. That is, in a series of hierarchical steps, geographically defined sampling units of decreasing size are selected with probability proportionate to their total number of occupied housing units. At the first stage, the primary areas (SMSAs, counties and county groups) are randomly selected; the second stage randomly selects area segments (housing unit clusters defined by Census Blocks or subsampled parts of selected Census Enumeration Districts); the third stage randomly samples housing units from the selected area segments; the final stage randomly selects a respondent from the eligible members of each sample household.

Prior to the first stage selection, the primary areas are stratified within each of the four Census regions by geography and size. One primary sampling unit is selected from each stratum using a controlled selection procedure. Sixteen of the 84 selections comprise the entire SMSA and are designated as "self-representing." The New York, Houston, and Atlanta SMSAs, for example, are self-representing.

The second stage sampling units are comprised of Census Blocks (in metropolitan primary areas) or Enumeration Districts (in some rural areas). Sampling of second stage units is performed with probability proportionate to number of occupied housing units in the area. Before second stage selection takes place, the second stage sampling units are stratified by geography, size, and in 36 of the 84 primary areas (where the data are available) by median per capita income. Within the 6 largest primary areas, between 6 to 25 segments are selected; in all other areas, 6 secondary selections are made.

At the third, and final stage, the SRC field staff lists all the housing units within each segment and selects a random subset. Once a household is selected, the interviewer lists all eligible adults residing there. To ensure that all people in the household have an equal probability of being chosen, in the final stage the interviewer uses a selection table to choose randomly the respondent to be interviewed.

In some years, the design was modified to include a component of 'panel' cases from the preceding Time-Series study. The 2000 Pre-Post Study used area probability sampling for one component of the total sample which was selected to be interviewed fact-to-face. A second 2000 Study component included respondents selected using RDD selection for telephone interviewing.

More information about Time-Series studies' design features
More information about non-Time-Series studies' design features
More information about RDD studies' design features

More information on response rates

Interviewing

For each survey, the NES Project Staff prepares the study questionnaires, relying on methods and standards that have been developed and refined over the past four decades. For face-to-face interviews, the NES Project Staff also prepares the interview booklets and visual aides that interviewers use. The booklets, in which the interviewer records the respondent's answers, will make heavy use of visual displays such as boxes, arrows, and checkpoints designed to make the survey instrument clear, reliable, and easy to administer.

The NES Pilot Studies, which are conducted by telephone, make use of the SRC Computer Assisted Telephone Interviewing (CATI) System. With CATI, the survey is embedded into a series of computer programs that display the questionnaire at a terminal, question-by-question. CATI permits complicated skip patterns and follow-up questions that are hand-tailored to prior responses. During the interviewing process, the computer program also checks for invalid responses, automatically moves the interviewer to the next question, and saves the entered data in machine-readable form. The NES Project Staff guides the writing of these computer applications and the subsequent testing to insure that the CATI applications are consistent with the intent of the Planning Committee.

Beginning in 1996, Computer Assisted Personal Interviewing (CAPI) replaced the pencil and paper questionnaires that have been used in the past for face-to-face interviewing. CAPI has the advantages of CATI transported into the respondent's living room via notebook computer. CAPI offers the capacity to enhance both the way in which questions are hand-tailored for respondents and the reliability of answers.

Established in 1946, the Field Section of the Survey Research Center has conducted the National Election Studies. The national field staff currently includes regional supervisors with substantial experience in interviewing, training, and personnel management. To assist the regional supervisors, the Field Section maintains a staff of Team Leaders and Team Leader Coordinators responsible for quality control. Information from the field is electronically transmitted to Ann Arbor on a weekly basis to permit close monitoring of costs and production. The Field Section maintains a national staff of hundreds of interviewers whose hiring, training, and supervision the regional supervisors coordinate. The interviewers are mature, well-educated, experienced, and represent the diversity of the primary areas in which they work. Newly hired SRC interviewers go through three full days of training that include instruction in the techniques of respondent selection, refusal conversion, question asking, clarification, probing, and data recording.

To facilitate the administration of the survey in a uniform fashion consistent with the intent of the Planning Committees, the NES Project Staff, in conjunction with the Field Section, prepares an interviewer study guide. This document includes field and sampling instructions, respondent selection criteria, a discussion of the interview cover sheet, a description of the objectives of the study, as well as item-by-item instructions on probing, the pronunciation of names, and the like.

Each NES study undergoes at least one pretest. Senior SRC interviewers question a small number of respondents (roughly 30) with the penultimate draft of the questionnaire. Following the interviews, the NES Project Staff and Principal Investigators participate in an intensive debriefing in which interviewers identify any problems with question ambiguity, ordering effects, or respondent fatigue.

Prior to the actual implementation of the national surveys, each regional supervisor conducts a pre-study conference with interviewers in the proximate area. At the conference, the supervisor reviews the study guide and addresses questions or problems raised as a result of practice interviews.

Active efforts are made to maximize response rate. Interviewer training demonstrates techniques for eliciting household and respondent cooperation and for converting those respondents who initially refuse. Continuous monitoring and evaluation of the response rate achieved by each interviewer provides opportunities for supervisors to intervene with additional training during the field period. Carefully crafted introductory interviewer scripts, a pamphlet and personal letter that describe NES and that includes the name and telephone number of the Principal Investigator, and an 800 number that respondents are invited to call to verify the study's legitimacy and importance all contribute to maximizing response rate. Small gifts, such as calendars and pens, and small respondent payments are now routinely used as incentives.

The SRC Field Section and the NES Project Staff carefully monitor the administration of each survey and the quality of each interviewer's work. SRC supervisors review initial interviews to insure that each interviewer is conducting the study properly and randomly call a subset of respondents to verify the completion of interviews. The NES Project Staff monitor the disposition of the sample and the efforts to increase the response rate. Beyond this, the NES Project Staff reviews every completed interview, to verify that the correct respondent was selected, and that the interviewer administered the questionnaire correctly. Such ongoing review of field production means that additional instructions can be sent to interviewers as necessary, and that incomplete or incorrect questionnaires can be returned to the field while the study is still in production.