Below are definitions related to common used words within the research industry.

CATI

Computer Assisted Telephone Interviewing, is a telephone surveying technique in which the interviewer follows a script provided by computer software..

CAWI

Computer Assisted Web Interviewing, an online surveying technique in which the interviewee follows a script provided by computer software.

Cross-tabulations

Data tables that present the results of an entire group of survey respondents in addition to results from any sub-groups of respondents.

Non-probability sampling

A sampling technique where all the subjects of a represented group or subgroup do not have equal chances of being selected. For example, a sample may only require 100 females between the ages of 26-34, not all females.

 

Open-end responses

In questionnaires, it is a response to a question cannot be answered with a simple “yes” or “no.” The response may require more words or thought from the responder.

Push poll

Involves an individual influencing another’s view by using manipulative questions in the guise of a poll. It’s usually done during political campaigns.

*Promark does NOT engage in push polls.*

For additional information, please refer to the AAPOR statement on push polls found here.

Quantitative v. Qualitative research

Quantitative research seeks to measure and systemize information by using numbers or statistical data. Results are more objective. Quantitative methods include telephone interviews, online surveys, and polls.

Qualitative research, however, generates data that cannot be recorded numerically, such as opinions or motivations. Results are more subjective. Qualitative research methods include focus groups and observation.

Quota sampling

A non-probability sampling technique in which representative data from a particular group is gathered.

 

 

Sampling

In statistics, it is the selection process of a subset of individuals from within a population to estimate the characteristics of the whole population.

Stratification

A sampling method where the researcher divides the survey population into separate groups called strata. Then, a probability sample (often a simple random sample) is drawn from each strata.

Stub-and-banner tables

A way to report information from two tables. One list will be tabulated in the columns, while the second list will be tabulated in the rows.

 

Survey research

A method of collecting information through questionnaires. Surveys are done via telephone, mail, and various digital methods.