MK473 Marketing Research: Measurement and Questionnaire Design

Flashcards covering basic concepts of measurement, four types of measurement scales (nominal, ordinal, interval, ratio), classification of scaling techniques (comparative and noncomparative including paired comparison, rank order, constant sum, Likert, and semantic differential), and the meaning of reliability and validity in marketing research.

What is the definition of measurement in marketing research?

Measurement is determining a description or amount of some property of an object of interest.

How do objective properties differ from subjective properties in measurement?

Objective properties are observable, tangible, and directly measurable (e.g., demographics), while subjective properties are unobservable, intangible, and must be translated onto a rating scale (e.g., attitudes and intentions).

What are the primary characteristics and common statistics used with a nominal measurement scale?

The numbers serve only as labels or tags for identifying and classifying objects without reflecting amount; permissible statistics are based on frequency counts like percentages and mode.

What defines an ordinal measurement scale, and what kind of information can it provide?

An ordinal scale is a ranking scale where numbers indicate the relative extent to which objects possess a characteristic (more or less), but not how much more or less. Statistics like percentile, quartile, and median can be used.

Describe the key features of an interval measurement scale and its limitation regarding ratios.

Numerically equal distances on the scale represent equal values in the characteristic being measured, allowing comparison of differences. The zero point is arbitrary, and it is not meaningful to take ratios of scale values.

What is the most comprehensive type of measurement scale, and what unique property does it possess?

The ratio scale possesses all the properties of the nominal, ordinal, and interval scales, including an absolute zero point, which makes it meaningful to compute ratios of scale values.

What is the fundamental difference between comparative and noncomparative scaling techniques?

Comparative scales involve the direct comparison of stimulus objects, yielding ordinal data, whereas noncomparative scales scale each object independently of others, generally yielding interval or ratio data.

How does the paired comparison scaling technique work, and what type of data does it yield?

A respondent is presented with two objects and asked to select one according to some criterion, yielding ordinal data.

Explain rank order scaling and the key limitation associated with it.

Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion, resulting in ordinal data. A limitation is that the respondent may dislike the top-ranked item in an absolute sense.

Describe Constant Sum Scaling and the type of data it produces.

Respondents allocate a constant sum of units (e.g., 100 points) to attributes of a product to reflect their importance; this technique results in ratio data.

What is a Likert scale, and what kind of data does it typically generate?

A Likert scale is a noncomparative scale where respondents indicate their degree of agreement or disagreement on a symmetric agree–disagree scale, measuring intensity of agreement and resulting in interval data.

How does the Semantic Differential scale measure perceptions, and what is a potential concern when using it?

It contains a series of bipolar adjectives for properties of an object, with respondents indicating their impressions along its continuum. A potential concern is the halo effect, where a general overall feeling about a brand could bias responses.

What does 'reliability' mean in the context of marketing research measurement?

Reliability is the degree to which the measure of a construct is consistent or dependable, implying consistency but not accuracy.

Define 'validity' in marketing research measurement.

Validity is the extent to which a measure adequately represents the underlying construct that it is supposed to measure, implying accuracy.