Question

Each of the following example involves a market researcher's need to measure some construct. Devise an appropriate scale for each one. In working out the scale, you are required to clearly indicate its scaling assumptions, the number of response categories, use or nonuse of a "no opinion" or neutral response category, and face validity.

Answer 1

T is testing five new flavors of yogurt. It wants to know how its customers rate each one on, . sweetness flavor strength richness of taste T needs to evaluate three subjective properties on the basis of taste tests of each yogurt flavor Following things need to be considered: A symmetric scale should not be used as it is quite unlikely that the flavors would be sour, weak, or not rich. There is zero possibility of a no opinion" reaction to the flavors. . A person cannot discriminate much in reporting a taste. Thus, the scale should not be more than five gradations with labels. This is because people cannot rank flavors with numbers. Not Strong Somewhat Strong Strong Very Strong Further, the face validity is obvious for this scale.

A percentage scale will be most appropriate as this is an instance of measuring intentions. Eleven categories-0% to 100%-can be used as doctors are expected to understand likelihoods of responses. Face validity, however, is apparent since the scale indicates the "chances of doing" rating.

A modified Likert scale would also be acceptable. For example, Indicate the degree to which you agree or disagree with the following statement. Strongly Disagree Neither Disagree Nor Agree Strongly Agree Statement Disagree Agree I will prescribe generic drugs. 4 Some doctors may have not yet decided on what they will do. Thus, a no opinion is appropriate. Face validity of the statement is apparent