Intro to Marketing Research: Measurement and Scaling - NonComparative Scales, Continuous Rating Scales Itemized Rating Scales Likert Semantic Differential Stapel

What It Is

Non-comparative scales are a type of measurement tool used in marketing research to collect data on a single attribute or characteristic. One notable example is the use of the Likert Scale in the American Customer Satisfaction Index (ACSI) survey, which measures customer satisfaction with various aspects of a product or service. This matters for marketing decision-making as it helps businesses understand customer perceptions and make data-driven decisions to improve their offerings.

Key Terms & Concepts

• Likert Scale: A type of itemized rating scale that measures attitudes or opinions on a continuum from strongly agree to strongly disagree.
  • Example: A survey question using a 5-point Likert Scale: "I am satisfied with the quality of this product."
  • Developed by Rensis Likert (1932)
• Semantic Differential: A type of itemized rating scale that measures attitudes or opinions by asking respondents to rate a product or service on a series of bipolar adjectives (e.g., good-bad, modern-ancient).
  • Example: A survey question using a Semantic Differential: "This product is modern vs. ancient."
  • Developed by Charles Osgood (1957)
• Stapel Scale: A type of itemized rating scale that measures attitudes or opinions by asking respondents to rate a product or service on a series of adjectives (e.g., excellent, good, fair, poor).
  • Example: A survey question using a Stapel Scale: "I rate this product as excellent, good, fair, or poor."
  • Developed by Stapel (1991)
• Continuous Rating Scale: A type of non-comparative scale that measures attitudes or opinions on a continuous scale (e.g., 0-100).
  • Example: A survey question using a Continuous Rating Scale: "How satisfied are you with this product? (0-100)"
• Mean: The average value of a set of data.
  • Formula: Mean = (?x) / n
  • Where x is each data point and n is the number of data points
• Standard Deviation: A measure of the spread or dispersion of a set of data.
  • Formula: SD = ?[(?(x - ?)^2) / (n - 1)]
  • Where x is each data point,-is the mean, and n is the number of data points
• Reliability: The consistency of a measure or scale.
  • Example: A survey question with high reliability would produce similar results when administered multiple times
• Validity: The accuracy of a measure or scale.
  • Example: A survey question with high validity would accurately measure the intended construct (e.g., customer satisfaction)
• Exploratory Research: Research aimed at generating new ideas or hypotheses.
  • Example: Conducting a survey to understand customer attitudes towards a new product
• Descriptive Research: Research aimed at describing a phenomenon or characteristic.
  • Example: Conducting a survey to describe customer demographics
• Type I Error: The probability of rejecting a true null hypothesis.
  • Formula:-= 1 - ?
  • Where-is the Type I error rate and-is the Type II error rate
• Type II Error: The probability of failing to reject a false null hypothesis.
  • Formula:-= 1 - ?
  • Where-is the Type II error rate and-is the Type I error rate

Common Misunderstandings

• Misunderstanding: A Likert Scale is a type of comparative scale.
• Correction: A Likert Scale is a type of non-comparative scale that measures attitudes or opinions on a continuum from strongly agree to strongly disagree.
• Misunderstanding: A Semantic Differential is a type of exploratory research tool.
• Correction: A Semantic Differential is a type of itemized rating scale that measures attitudes or opinions by asking respondents to rate a product or service on a series of bipolar adjectives.
• Misunderstanding: A Stapel Scale is a type of continuous rating scale.
• Correction: A Stapel Scale is a type of itemized rating scale that measures attitudes or opinions by asking respondents to rate a product or service on a series of adjectives.

Quick Application / Identification

Scenario: A marketing researcher wants to measure customer satisfaction with a new product. Which type of non-comparative scale would be most appropriate to use?

Answer: A Likert Scale. Explanation: A Likert Scale is a type of non-comparative scale that measures attitudes or opinions on a continuum from strongly agree to strongly disagree, making it suitable for measuring customer satisfaction.

Scenario: A marketing researcher wants to measure customer attitudes towards a new product. Which type of non-comparative scale would be most appropriate to use?

Answer: A Semantic Differential. Explanation: A Semantic Differential is a type of itemized rating scale that measures attitudes or opinions by asking respondents to rate a product or service on a series of bipolar adjectives, making it suitable for measuring customer attitudes.

Scenario: A marketing researcher wants to measure customer satisfaction with a new product on a continuous scale. Which type of non-comparative scale would be most appropriate to use?

Answer: A Continuous Rating Scale. Explanation: A Continuous Rating Scale is a type of non-comparative scale that measures attitudes or opinions on a continuous scale, making it suitable for measuring customer satisfaction on a continuous scale.

Last-Minute Revision

• A Likert Scale has 5-7 points, but can have more or fewer points depending on the researcher's discretion.
• A Semantic Differential has 7-10 bipolar adjectives, but can have more or fewer adjectives depending on the researcher's discretion.
• A Stapel Scale has 4-5 points, but can have more or fewer points depending on the researcher's discretion.
• The mean is sensitive to outliers, which can affect the reliability of the measure.
• The standard deviation is a measure of the spread or dispersion of a set of data, but can be affected by outliers.
• Reliability and validity are two distinct concepts in marketing research.
• Exploratory research is aimed at generating new ideas or hypotheses, while descriptive research is aimed at describing a phenomenon or characteristic.
• Type I error is the probability of rejecting a true null hypothesis, while Type II error is the probability of failing to reject a false null hypothesis.
• The formula for calculating the mean is ?x / n, where x is each data point and n is the number of data points.
• The formula for calculating the standard deviation is ?[(?(x - ?)^2) / (n - 1)], where x is each data point,-is the mean, and n is the number of data points.