Intro to Marketing Research: Quantitative Research - Questionnaire Design, Structured vs. Unstructured Questions Scales Likert Semantic Differential Stapel Constant Sum Rank Order Open-Ended Closed-Ended

Questionnaire Design

What It Is

Questionnaire design is the process of creating a set of questions to collect data from respondents in a survey or research study. The goal is to gather accurate and reliable information that can inform marketing decisions. A well-designed questionnaire can make a significant difference in the quality of data collected, which is essential for making informed marketing decisions. For example, the American Customer Satisfaction Index (ACSI) uses a structured questionnaire to measure customer satisfaction across various industries. This matters for marketing decision-making because it helps businesses understand their customers' needs and preferences, enabling them to make data-driven decisions.

Key Terms & Concepts

• Structured Questions: Questions with a fixed set of response options, such as multiple-choice or Likert scales.
  • Example: A survey asking respondents to rate their satisfaction with a product on a scale of 1-5.
• Unstructured Questions: Open-ended questions that allow respondents to provide their own answers.
  • Example: A survey asking respondents to describe their favorite product feature.
• Likert Scale: A scale used to measure attitudes or opinions, typically ranging from 1 (strongly disagree) to 5 (strongly agree).
  • Example: A survey asking respondents to rate their agreement with the statement "I love this product."
• Semantic Differential Scale: A scale used to measure attitudes or opinions, typically ranging from 1 (very bad) to 7 (very good).
  • Example: A survey asking respondents to rate their opinion of a product on a scale from very bad to very good.
• Stapel Scale: A scale used to measure attitudes or opinions, typically ranging from 1 (very bad) to 7 (very good), with a neutral point in the middle.
  • Example: A survey asking respondents to rate their opinion of a product on a scale from very bad to very good, with a neutral point in the middle.
• Constant Sum Scale: A scale where respondents are asked to allocate a fixed number of points across multiple options.
  • Example: A survey asking respondents to allocate 10 points across different product features.
• Rank Order Scale: A scale where respondents are asked to rank options in order of preference.
  • Example: A survey asking respondents to rank their favorite product features in order of importance.
• Open-Ended Questions: Questions that allow respondents to provide their own answers.
  • Example: A survey asking respondents to describe their favorite product feature.
• Closed-Ended Questions: Questions with a fixed set of response options.
  • Example: A survey asking respondents to rate their satisfaction with a product on a scale of 1-5.
• Reliability: The consistency of a measure or scale.
  • Example: A survey with a high reliability coefficient (e.g., Cronbach's alpha > 0.7) indicates that the scale is measuring the same thing consistently.
• Validity: The accuracy of a measure or scale.
  • Example: A survey with high face validity (i.e., it measures what it claims to measure) indicates that the scale is valid.
• Type I Error: The probability of rejecting a true null hypothesis.
  • Example: A survey with a Type I error rate of 0.05 indicates that there is a 5% chance of rejecting a true null hypothesis.
• Type II Error: The probability of failing to reject a false null hypothesis.
  • Example: A survey with a Type II error rate of 0.2 indicates that there is a 20% chance of failing to reject a false null hypothesis.
• Cronbach's Alpha: A coefficient used to measure the reliability of a scale.
  • Formula: Cronbach's alpha = (k / (k - 1)) * (1 - (^2_x / ?^2_T))
  • Where k is the number of items, ?^2_x is the variance of each item, and ?^2_T is the total variance.
• Exploratory Research: Research aimed at generating new ideas or hypotheses.
  • Example: A survey aimed at understanding customer preferences for a new product.
• Descriptive Research: Research aimed at describing existing phenomena.
  • Example: A survey aimed at understanding customer demographics.
• Regression Equation: A statistical model used to predict a continuous outcome variable.
  • Formula: Y = ?0 + ?1X + ?
  • Where Y is the outcome variable, X is the predictor variable, ?0 is the intercept, ?1 is the slope, and-is the error term.

Common Misunderstandings

• Misunderstanding: A Likert scale is a type of open-ended question.
• Correction: A Likert scale is a type of structured question with a fixed set of response options.
• Misunderstanding: A Stapel scale is a type of scale used to measure attitudes or opinions.
• Correction: A Stapel scale is a type of scale used to measure attitudes or opinions, but it is not as commonly used as Likert or Semantic Differential scales.
• Misunderstanding: A Constant Sum scale is a type of rank order scale.
• Correction: A Constant Sum scale is a type of scale where respondents are asked to allocate a fixed number of points across multiple options, but it is not a rank order scale.

Quick Application / Identification

Scenario: A marketing researcher wants to measure customer satisfaction with a new product. Which type of question would be most suitable for this purpose?

Answer: Likert Scale. A Likert scale is a structured question with a fixed set of response options, making it suitable for measuring attitudes or opinions.

Explanation: A Likert scale is a good choice for measuring customer satisfaction because it allows respondents to rate their satisfaction on a scale from 1 to 5, providing a clear and concise measure of their opinion.

Last-Minute Revision

• A survey with a high reliability coefficient (e.g., Cronbach's alpha > 0.7) indicates that the scale is measuring the same thing consistently.
• A survey with high face validity (i.e., it measures what it claims to measure) indicates that the scale is valid.
• A survey with a Type I error rate of 0.05 indicates that there is a 5% chance of rejecting a true null hypothesis.
• A survey with a Type II error rate of 0.2 indicates that there is a 20% chance of failing to reject a false null hypothesis.
• Cronbach's alpha = (k / (k - 1)) * (1 - (^2_x / ?^2_T))
• Exploratory research is aimed at generating new ideas or hypotheses.
• Descriptive research is aimed at describing existing phenomena.
• A regression equation is a statistical model used to predict a continuous outcome variable.
• Y = ?0 + ?1X + ?
• A Constant Sum scale is a type of scale where respondents are asked to allocate a fixed number of points across multiple options.
• A rank order scale is a type of scale where respondents are asked to rank options in order of preference.