chpt 8

• Measurement


  Determining a description or amount of some property of an object that is of research interest
• Properties/Variables


  Specific features or characteristics of an object that can be used to distinguish it from another object
• Types of properties


  • Objective
  • Subjective
• Objective properties


  Observable and tangible, physically verifiable characteristics
• Subjective properties


  Expressed, unobservable and intangible, must be translated onto a rating scale
• Types of measures


  • Nominal
  • Ordinal
  • Interval
  • Ratio
• Nominal measures


  Label objects, data can only be categorized
• Ordinal measures


  Indicate relative size differences between objects
• Interval scales


  Measure unobservable constructs, distance between each level is known
• Ratio scales


  Have a true zero point
• Nominal scale questions


  • Race, religion, type of dwelling, gender, brand last purchased, buyer/nonbuyer
• Ordinal scale questions


  • Ranking brand choices

  
• Ratio scale measures


  • Number of purchases, dollars spent, miles traveled, number of children, salary
• Interval scale questions


  Rating scales for subjective properties, distance is normally defined as one scale unit
• Interval scales commonly used


  • Likert scale
  • Semantic differential scale
  • Stapel scale
  • Slider scales
• Likert scale


  Measures intensity of agreement or disagreement on a symmetric agree-disagree scale
• Questionnaire


  • Translates research objectives into specific questions
  • Standardises questions and response categories
  • Serves as a record of the research
  • Can speed up data analysis
  • Contains information for reliability and validity assessments
• Questionnaire design process


  1. Consider question formats

  2. Consider survey factors

  3. Word questions carefully

  4. Organise questionnaire layout
• Marketing researchers develop questions to measure attitudes, beliefs, behaviors, and demographics
• Four "don'ts" of question wording


  • Do not lead the respondent
  • Do not use loaded wording
  • Do not use double-barreled questions
  • Do not overstate the case