METHODOLOGY

Survey Methodology

The Elon University Poll is conducted using a stratified random sample of households with telephones in the population of interest – in most cases this means the citizens in North Carolina. The sample of telephone numbers for the survey is obtained from Survey Sampling International, LLC.

Selection of Households

To equalize the probability of telephone selection, sample telephone numbers are systematically stratified according to subpopulation strata (e.g., a zip code, a county, a state, etc.), which yields a sample from telephone exchanges in proportion to each exchange's share of telephone households in the population of interest. Estimates of telephone households in the population of interest are generally obtained from several databases. Samples of telephone numbers are distributed across all eligible blocks of numbers in proportion to the density of listed households assigned in the population of interest according to a specified subpopulation stratum. Upon determining the projected (or preferred) sample size, a sampling interval is calculated by summing the number of listed residential numbers in each eligible block within the population of interest and dividing that sum by the number of sampling points assigned to the population. From a random start between zero and the sampling interval, blocks are systematically selected in proportion to the density of listed household "working blocks." A block (also known as a bank) is a set of contiguous numbers identified by the first two digits of the last four digits of a telephone number. A working block contains three or more working telephone numbers. Exchanges are assigned to a population on the basis of all eligible blocks in proportion to the density of working telephone households. Once each population's proportion of telephone households is determined, then a sampling interval, based on that proportion, is calculated and specific exchanges and numbers are randomly selected. Because exchanges and numbers are randomly selected by the computer, unlisted as well as listed telephone numbers are included in the sample. Thus, the sample of telephone numbers generated for the population of interest constitutes a random sample of telephone households of the population, stratified by exchange.  

Procedures Used for Conducting the Poll

The Elon University Poll usually conducts surveys Monday through Thursday evenings; occasionally we will survey people on Sundays. During these times calls are made from 5-9 p.m. EST during the week and 1-6 p.m. EST on weekends. The Elon University Poll uses CATI system software (computer assisted telephone interviewing) in the administration of surveys. For each working telephone number in the sample, several attempts are made to reach a household. Only individuals in households 18 years or older are interviewed; those reached at business or work numbers are not interviewed. Within each household, one adult is generally selected based on whether s/he is the oldest or youngest adult in the home.  Interviews, which are conducted by live interviewers, are completed with adults from households in the target population as specified. Interviews for our surveys are completed with several hundred adults from households in the target population. For example, with a sample size of 500, there is a 95 percent probability that our survey results are within plus or minus 4.5 percentage points (the margin of sampling error) of the actual population distribution for any given question. For sub-samples (a subgroup selected from the overall sample), the margin of error is higher depending on the size of the subsample. When we use a subsample, we identify these results as being from a subsample and provide the total number of respondents and margin of error for that subsample. In reporting our results, we note any use of a subsample where applicable. 

Because our surveys are based on probability sampling, there are a variety of factors that prevent these results from being perfect, complete depictions of the population; the foremost example is that of margin of sampling error (as noted above). With all probability samples, there are theoretical and practical difficulties estimating population characteristics (or parameters). Thus, while efforts are made to reduce or lessen such threats, sampling error as well as other sources of error – while not all inclusive, examples of other error effects are non-response rates, question order effects, question wording effects, etc. – are present in surveys derived from probability samples.

Question Construction and Question Order

The Elon University Poll provides the questions as worded and the order in which these questions are administered (to respondents). Conspicuous in reviewing some questions is the “bracketed” information.  Information contained within brackets ( [ ] ) denotes response options as provided in the question; this bracketed information is rotated per question during the administration of our surveys to ensure that respondents do not receive a set order of response options presented to them, which also maintains question construction integrity by avoiding respondent acquiescence based on question composition. Some questions use a probe maneuver to determine a respondent’s intensity of perspective. Probe techniques used in our questionnaires mainly consist of asking a respondent if their response is more intense than initially provided.  For example, upon indicating whether s/he is satisfied or dissatisfied, we asked the respondent “would you say you are very ______”. This technique is employed in some questions as opposed to specifying the full range of choices in the question. Though specifying the full range of options in questions is a commonly accepted practice in survey research, we sometimes prefer that the respondent determine whether their perspective is stronger or more intense for which the probe technique used. Probed responses are usually denoted by “(p)”. Another method for acquiring information from respondents is to ask an “open-ended” question. The open-ended question is a question for which no response options are provided, i.e., it is entirely up to the respondent to provide the response information. In reporting our results, we designate those responses that are volunteered by respondents. As not all response options are offered to those taking the survey, some respondents offer or volunteer response options. Though not all volunteered options can be anticipated, the more common options are noted. Volunteered responses are usually noted by “(v)”.

The Elon University Poll

The Elon University Poll is conducted under the auspices of the Center for Public Opinion Polling (Hunter Bacot, Director; Mileah Kromer, Assistant Director), which is a constituent part of the Institute for Politics and Public Affairs (George Taylor, Director); both these organizations are housed in the department of political science at Elon University.  These academic units are part of Elon College, the College of Arts and Sciences at Elon University, which is under the direction of Pam Kiser (Dean).

The Elon University administration, led by Dr. Leo Lambert, president of the university, fully support the Elon University Poll as part of its service commitment to state, regional, and national constituents.  Bacot, a professor in the department of political science, directs the Elon University Poll. Kromer, an assistant professor in the department of political science, assists in the direction of the Elon University Poll. Elon University students participate in the development and administration of the survey as part of the University’s commitment to experiential learning where “students learn through doing.”