7400.685-080 - Research Methods in FCS
School of Family and Consumer Sciences
Spring Semesters - Tuesday Evenings 5:20-7:55pm
Instructor: David D. Witt, Ph.D.
Key Terms Part 2

KEY TERMS #3 - Measurement - Use each term in a sentence to illustrate your understanding of the concept.
  1. Operationalization of a concept means translating the ideal into a representation in real terms, such as the idea of AGE translated into answers to the question "HOW OLD WERE YOU AT THE TIME OF YOUR LAST BIRTHDAY.  Researchers translate the idea of what they want to measure into the real measure.
  2. Construct validity is the degree to which inferences can legitimately be made from the operationalizations in your study to the theoretical constructs on which those operationalizations are based. To evaluate this type of validity, the dependent "construct" in question should be correlated to other variables known to be related to the dependent variable.
  3. Content validity refers to a variable's ability to cover the entire content domain of the theoretical construct. For example, in many cases, a theoretical construct is a broad idea that requires more measurement than a single item can accomplish, such as socioeconomic status (which requires measures of income, education, and occupational prestige).
  4. Face validity simply means that a variable, “on its face”, seems like a good translation of the construct - a good measure.
  5. Mono-method bias is a threat to construct validity that occurs because you use only a single method of measurement.  To strengthen construct validity, multiple methods should be employed.
  6. Predictive validity is a type of construct validity based on the idea that your measure is able to predict what it theoretically should be able to predict.
  7. Reliability is the degree to which a measure is consistent or dependable, giving the same result every time it is used. Think of reliability as the accuracy of a rifle.
  8. Threats to construct validity are factors that lead to incorrect conclusions about whether your operationalized variables reflect well the construct they are intended to represent.
Key Terms #4 - Survey Research - Use each term in a sentence to illustrate your understanding of the concept.
  1. Dichotomous response format is a questionnaire item with two possible responses. It is undesirable in research.
  2. Electronic survey is any survey instrument that is administered to participants through an electronic medium, such as email or the web.
  3. A Filter or contingency question is one in which respondents are asked to determine whether they are qualified or experienced enough to answer a subsequent one.
  4. A Focus group is a form of measurement where group input on one or more topics is collected from participants. The discussion is structured and guided by a facilitator.
  5. Level of measurement is a concept that determines the appropriate statistical rigor for collected data.
    1. A Nominal level measure has a number beside each choice where the number has no meaning except as a placeholder for that response, such as 1=male and 2=female, eye color, etc.
    2. An Ordinal measure would ask respondents to rank their feelings, attitudes, or preferences. For example "low", "medium" and "high" tells us that low is less than high, but does not say anything about how much less it is from high.
    3. Interval-level measures are like Ordinal measures with the added feature of having the same interval from one response to the next.  Degrees on a thermometer, inches on a ruler, blood cell count are examples
    4. Ratio-Level response format has the qualities of Interval-level but also has a non-arbitrary zero  point.
  6. Scaling involves the construction of a measurement instrument that associates qualitative constructs with quantitative metric units. The result would be a point on the scale that characterizes an attitude, value, or other score.
  7. A Likert scale is a response format that uses a multi-point integer scale. For example, a scale where 1=strongly disagree, 2=disagree, 3=no opinion, 4=agree and 5=strongly agree would be a Likert-type scale.
  8. Response brackets: A question response type that includes groups of answers, such as between 30 and 39 years old, or between $50,000 and $59,000 annual income.
  9. Semantic differential scale is a scaling method in which an object is assessed by the respondent on a set of bipolar adjective pairs. For example, rate yourself on these items:
                           Weak   ---1---2---3---4---5 Strong
                           Gabby ---1---2---3---4---5 Quiet
  10. Unstructured response formats are essentially open-ended questions, such as "Tell me about your first date: ___________________________________________
  11. A Structured response format is one in which the response set is determined during questionnaire construction, as in a regular questionnaire item with specific choices.
  12. Guttman scale is one in which the items are assigned values that allow them to be placed in a cumulative ordering with respect to the construct being scaled.  The Bogardus social distance scale is a Guttman scale designed to empirically measure people's willingness to participate in social contacts with increasing degrees of closeness. The scale asks people the extent to which they would be accepting of each group (a score of 1.00 for a group is taken to indicate no social distance):
  1. As close relatives by marriage (score 1.00)
  2. As my close personal friends (2.00)
  3. As neighbors on the same street (3.00)
  4. As co-workers in the same occupation (4.00)
  5. As citizens in my country (5.00)
  6. As only visitors in my country (6.00)
  7. Would exclude from my country (7.00)