Glossary of Survey Terminology

Surveys are an effective way for organizations to collect insights and feedback from customers, patients, employees and other audiences. Here are some of the most commonly-used survey terms and their definitions. From aggregate data to validity, we’ve listed the terms in alphabetical order.

Aggregate data – A type of data that combines individual pieces of collected data into one larger dataset. Analyzing aggregate data can help shine light on trends that might otherwise be missed when looking at individual responses.
Closed-ended question – A question that provides respondents with a set of predefined answer choices from which to select. These choices may include a simple yes/no response, multiple choice options or rating scales. Closed-ended questions are often used in quantitative research because they provide specific and measurable data that can be analyzed and compared.
Cognitive burden – The mental effort it takes for survey participants to understand and answer questions in a survey. It includes factors like the complexity of the language used, the amount of time required to complete the survey and the difficulty of comprehension posed by certain types of questions.
Completion rate – The percentage of survey respondents who have successfully completed a given survey. A higher completion rate indicates that the survey was easier to complete, more engaging and had fewer technical issues, while a lower completion rate may suggest there were problems with the survey.
Conclusion validity – The degree to which a survey’s conclusions accurately reflect reality.
Disaggregate data – A type of data where elements have been separated from the whole and arranged into smaller groups or categories. For example, data broken down by gender, income or level of education. Disaggregate data is often used to analyze trends and draw conclusions that may not be evident in aggregate data.
Demographic questions – Questions that are designed to reveal information about the characteristics of the participants, such as age, gender, ethnicity, income level, occupation and marital status. These types of questions allow researchers to better understand and analyze the results of the survey by segmenting responses according to these characteristics.
Double-barreled question – A question that has two parts to it within the same sentence. It can lead to confusion and inaccurate survey results since the respondent may not be sure which part of the question they are being asked to answer.
Leading question – A question that suggests or implies the desired answer and might influence respondents to give a particular response. Leading questions are considered unethical because they introduce bias into collected data.
Likert-type scale – A type of scale that consists of a series of statements that respondents rate from strongly agree to strongly disagree, with various degrees of agreement in between. It is designed to measure attitudes and opinions by asking respondents to indicate their level of agreement or disagreement with each statement.
Loaded question – A question that contains an assumption and is often worded so that the respondent has few options other than agreeing with what is being implied.
Multivariate analysis – A technique used to analyze the relationships between multiple variables simultaneously.
Open-ended question – A type of question that does not have a set response. Respondents can provide their own answers rather than having to choose from predefined options.
Qualitative research – Research that uses non-numerical data to make conclusions about a population. It can be used to gain greater insight into the reasons for why something happens or how people think about certain issues.
Quantitative research – Research that uses numerical data to make conclusions about a population. It can be used to compare different groups, measure the prevalence of certain opinions or behaviors, etc.
Random sampling – A technique where participants are selected at random from the population of interest. Each potential participant has an equal chance of being selected for the survey. Random sampling helps remove bias that could be introduced by selecting certain individuals or groups over others.
Reliability – A measure of consistency and the degree to which results obtained from the same survey instrument or method can be replicated. Reliability helps ensure more accurate and valid data.
Research sponsor – An individual, group or organization that provides funding and/or other resources for the purpose of conducting a survey.
Response coding – The process of assigning meaningful labels or codes to data collected from survey questions in order to make it easier to analyze and interpret. Organizing respondents’ answers into categories can then be used for further analysis, such as identifying patterns, trends and relationships within the data.
Response rate – A measure of the number of people who responded to a survey compared to the number of people who were invited or asked to complete the survey.
Sample – A selection of individuals that represent the characteristics of a larger population.
Sample size – The number of participants included in a survey or study. Larger sample sizes tend to provide more reliable results than smaller samples.
Screening question – A type of question used to filter out respondents who are not qualified for a study. It typically asks about the respondent’s background, such as gender, age, location or occupation. Screening questions help researchers target an appropriate audience for their research and ensure that the results reflect the desired demographic group.
Self-selection bias – A type of bias that comes about when research participants select themselves into the sample rather than being randomly selected. This type of bias can lead to inaccurate results because the sample may be skewed towards people who are more likely to respond positively or negatively.
Statistical significance – A term used to describe the likelihood that a relationship or difference between two or more variables is not due to chance.
Survey – A structured set of questions used to collect information from respondents about their experiences, opinions, attitudes, beliefs and behaviors. Surveys can be administered in person, by phone, online or through the mail.
Univariate analysis – A statistical method that focuses on analyzing one variable at a time.
Validity – A term that refers to whether or not a survey’s questions are measuring what they intend to measure, and so whether the answers collected from respondents accurately reflect their attitudes, beliefs and behaviors.

If our Glossary of Survey Terminology has been helpful to you, we encourage you to share it with a colleague or let us know.