Marketing Research Glossary - N

NA (No Answer): An abbreviation to indicate no answer to a question.

NAICS: The North American Industry Classification System (NAICS) is the replacement for the U.S. Standard Industrial Classification (SIC) system. NAICS was developed jointly by the U.S., Canada, and Mexico to provide comparability in statistics about business activity across North America.

Name Testing: A research technique used in new product development to identify the best names for a new product or service. Learn More

NameScreen®: Decision Analyst's proprietary Internet-based system used to identify the best names for a new product or service. Learn More

Nationally Representative Sample: A sample that is representative of the total U.S. population. Icion® is the name of Decision Analyst's sophisticated software that pulls nationally representative samples with unequaled levels of precision.

Net: A grouping of answer codes to open-ended questions. For example, all answers related to "product quality" might be grouped together in a net (with all duplication of respondents eliminated) to see how many respondents mentioned product quality.

Net Incidence: The percentage of respondents who qualified to participate in a survey after all qualifying questions are answered. The greater the number of qualifying questions, the lower the net incidence is.

Net Lift Modeling: A predictive analytics technique that incrementally measures a marketing campaign’s effect on a consumer. Typically, a treated group (sees the ad), and a control group (does not see the ad) are compared together. Learn More

Network Flow Models: Network flow models are used in Operations Research and Management Science. Network flow models are linear programming models used for optimizing the performance (or flow) of a network (transportation, shipping, communications, etc.). Learn More

Neural Network: In marketing research, neural networks are used as data analysis tools. By harnessing a computer's ability to process millions of calculations quickly, neural networks can identify patterns, draw abstractions, and uncover relationships in large amounts of data.

New Product Concept Testing: The testing of new product ideas at the "concept" stage (before actual products are created). A new product concept typically includes an illustration of the product along with a description of its features and benefits. Concepts are written in an informative, descriptive style without the use of "advertising" language. The establishing of concept standards or concept guidelines are essential to the success of any new product concept-testing program. ConceptTest® is the name of Decision Analyst's advanced concept-testing system. Learn More

New Product Prototype: A full-scale working model of a product. Prototypes are typically used for testing and evaluation among prospective customers before putting the product into mass production.

Nixie: Mailing piece returned to mailer by the Postal Service because of an incorrect or undeliverable name or address. The nixie rate varies depending on the source of the mailing list.

Noise: Anything that interferes with the measurement of a marketing research variable. For example, competitive activity creates "noise" in the marketplace that makes it difficult for a manufacturer to understand the results of his own marketing actions.

Nominal Grouping Technique (NGT): A qualitative method for individuals or small groups to generate many ideas on a topic (with no criticism permitted), then they secretly vote on the importance of each idea, followed by discussion and exploration of the most important topics or ideas. A NGT session might involve a number of sequential votes to focus the attention and energy of the group or groups on the most important issues or topics. Sometimes seen as an alternative technique to brainstorming.

Nominal Scales: Scales that subdivide data into mutually exclusive categories. For example, the scale "male or female" divides the population into two mutually exclusive groups.

Nonbalanced Scales: Answer choices or answer scales with more positive answer choices than negative answer choices, or vice versa.

Noncomparative: A measurement made in isolation without reference to other items, things, or people. The term Monadic has similar a meaning.

Nonfamily Household: A household made up of a person living alone or living with nonrelatives, as defined by the Census Bureau.

Nonprobability Samples: Any samples which are not probability samples. Nonprobability samples are generally not representative of the target population.

Nonrandom: Events and occurrences with unequal probabilities of occurrence. In contrast, random events and occurrences have equal probabilities of occurrence.

Nonresponse Bias: The error that results from a difference between those who respond to a survey and those who do not respond.

Nonsampling Error: The many sources of potential bias in a survey other than sampling error. All statistical theory is based on sampling variation or sampling error.

Norm Or Norms: An average survey research result to a standard question, typically in some type of standardized research service, such as copy-testing systems or concept-testing systems. For example, Decision Analyst maintains massive databases of historical norms for its many standardized testing services (CopyTest®, ConceptTest®, PackageTest®, and so on).

Normal Distribution: A continuous bell-shaped distribution that is balanced about the mean, median, and mode. Sixty-eight percent of the observations fall within plus or minus one standard deviation of the mean, approximately 95% fall within plus or minus two standard deviations, and approximately 99.5% fall within plus or minus three standard deviations.

Normative Data: Measures of central tendency, such as mean, median, and mode. The term is also used to refer to "norms" of test results in databases.

No-Show: A focus group participant who agrees to come to a session and is confirmed the night before, but nonetheless does not show up for the session. Focus group facilities compensate for no-shows by overrecruiting two to four people for each focus group.

Nth Selection: A sampling process of selecting every third record, or every tenth record, or every 20th respondent, etc. To determine the nth interval, divide the total number of sampling units (respondents) by the number of records that will need to be selected to achieve the desired number of completed interviews. Also known as Interval Selection.

Null Hypothesis: The hypothesis or premise that is being tested in a statistical test of significance.

Numeric Database: A database containing survey data or other types of data.

Numeric Open-End (NO): Question type that only allows for numeric data. Includes dollar amounts, zip codes, etc.

Numeric Open End Example

Contact Decision Analyst

If you would like more information on Marketing Research, please contact Jerry W. Thomas by emailing or calling 1-817-640-6166.