Term
|
Definition
A generalized idea about a class of objects, attributes, occurrences, or processes
- Ex) customer satisfaction |
|
|
Term
|
Definition
| Finding scales that measure the properties of the concept |
|
|
Term
|
Definition
| Device that provides a range of values to measure the concept |
|
|
Term
|
Definition
| The way a certain value on a scale corresponds to some true value of concept |
|
|
Term
|
Definition
Different values of a concept
- Ex) Male or female |
|
|
Term
|
Definition
| Concepts measured with multiple variables |
|
|
Term
| Levels of Scale Measurement |
|
Definition
- Nominal
- Ordinal
- Interval
- Ratio |
|
|
Term
| Levels of Scale Measurement - Nominal |
|
Definition
- Assigns a value to an object for classification
- Ex) gender: yes-no |
|
|
Term
| Levels of Scale Measurement - Ordinal |
|
Definition
- Ranking scales - show order
- Have nominal properties
- Ex) level of education |
|
|
Term
| Levels of Scale Measurement - Interval |
|
Definition
- Information about differences in quantities of a concept
- Have nominal/ordinal properties
- Do not perfectly describe something (no absolute zero)
- Ex) Temperature in Fahrenheit and Celsius |
|
|
Term
| Levels of Scale Measurement - Ratio |
|
Definition
- Highest form of measurement
- Represent absolute quantities
- Absolute zero
- Ex) amount purchased
- Ex) Kelvin scale |
|
|
Term
| Mathematical and Statistical Analysis of Scales |
|
Definition
- Discrete measures (only take on one value)
- Continues measures (shows intensity of a concept by assigning values along a scale) --> Ex) strongly agree |
|
|
Term
|
Definition
- Value = how much of the concept beng measured is associated with an observation
- Usually combination of several unrelated variables
- Ex) social class index: income, occupation, etc. |
|
|
Term
|
Definition
- Multiple variables
- Differs from index measures because the variables are related to each other |
|
|
Term
| Computing Scale Values - Summated Scale |
|
Definition
| - Adding together the values |
|
|
Term
| Computing Scale Values - Reverse Coding |
|
Definition
| - Value assigned for a response is treated opposite from the other items |
|
|
Term
|
Definition
| - Degree the measures are free from random error and yield consistent results |
|
|
Term
|
Definition
- Extent to which each indicator of a concept converges on some common meaning
- Measured by correlating scores on subsets of items making up a scale |
|
|
Term
| Testing Reliability - Split-half method |
|
Definition
| Checking the results of one half of the items against the results from the other half |
|
|
Term
| Testing Reliability - Coefficient alpha |
|
Definition
- Most commonly used method
- Represents the average of all possible split-half reliabilities |
|
|
Term
| Testing Reliability - Test-retest method |
|
Definition
| - Administer the same scale to the same respondents at a different time |
|
|
Term
|
Definition
| Extent to which a score truthfully represents a concept |
|
|
Term
|
Definition
- Does the scale measure what it is supposed to be measured?
- Does the measure correlate with other measures of the same concept?
- Does the behavior expected predict actual observed behavior? |
|
|
Term
| Types of Validity - Face (content) |
|
Definition
| Does content measure what it set out to measure? |
|
|
Term
| Types of Validity - Criterion |
|
Definition
| Does it correlate with standard measures of similar constructs? |
|
|
Term
| Types of Validity - Construct |
|
Definition
| Does it measure only one thing? |
|
|
Term
| Types of Validity - Convergent |
|
Definition
|
|
Term
| Types of Validity - Discriminant |
|
Definition
You don't want it to measure multiple things
- Scale should not correlate too highly with a measure of a different construct |
|
|
Term
|
Definition
- Global evaluation
- Consistently respond to various things
- Long-lived
- Magnitude and direction |
|
|
Term
|
Definition
- Affective component
- Cognitive component
- Behavioral component |
|
|
Term
|
Definition
- Ranking
- Rating
- Sorting
- Choose an alternative
- Category scale
- Simple Attitude scale
- Likert Scale
- Semantic Differential
- Constant-Sum Scale
- Graphic Rating Scale |
|
|
Term
| Attitude Rating Scales - Ranking |
|
Definition
- Rank on the basis of a characteristic or stimulus
- Disadvantage: do not have an accurate idea of magnitude |
|
|
Term
| Attitude Rating Scales - Rating |
|
Definition
| - Estimate the magnitude of something an object possesses |
|
|
Term
| Attitude Rating Scales - Sorting |
|
Definition
| - EX) Cards with brand names on them are put into piles and the piles have something in common |
|
|
Term
| Attitude Rating Scales - Category Scale |
|
Definition
More than two response categories
- Question construct = critical
- Good for long questionnaires or when respondents are not well educated
- Ex) Very important, somewhat important, not important |
|
|
Term
| Attitude Rating Scales - Simple Attitude Scale |
|
Definition
Two response categories
- Ex) Agree, disagree |
|
|
Term
| Attitude Rating Scales - Likert Scale |
|
Definition
- Most popular method
- How strongly the agree or disagree with statements |
|
|
Term
| Attitude Rating Scales - Semantic Differential |
|
Definition
- Bipolar adjectives at opposite ends of the scale
- Ex) Simple __ __ __ __ __ Complex |
|
|
Term
| Attitude Rating Scales - Constant-Sum Scale |
|
Definition
Divide a constant sum to indicate the relative importance of attributes
- Ex) Divide 100 points among the following brands according to your preference for the brand |
|
|
Term
| Attitude Rating Scales - Graphic Rating Scale |
|
Definition
Choosing any point along a graphic continuum
- Advantage: Allows researcher to choose any interval for scoring purposes
- Disadvantage: no standard answers
- Ex) Not important ------------------important |
|
|
Term
|
Definition
- Pick the preferred object between two
- More than two objects can be presented, but comparisons must be made in pairs
- Ex) MedBand is better or Super-Aid is better |
|
|
Term
|
Definition
- Asks about a single concept in isolation
- Respondent is not given a specific frame of reference
- Ex) Now that you've had your car for 1 year, tell us how satisfied you are with its engine power/pickup
completely dissatisfied, dissatisfied, somewhat satisfied, etc. |
|
|
Term
|
Definition
- Asks respondent to rate a concept in comparison with a benchmark explicitly used as a frame of reference
- Ex) Indicate how the amount of authority in your present position compares with the amount of authority that would be ideal for this position
too much, about right, too little |
|
|
Term
| What type of Category Label (if any)? |
|
Definition
| - Verbal labels tend to work better because they help respondents understand response positions |
|
|
Term
|
Definition
Equal number of positive and negative categories
- Neutral point in the center
- Ex) Satisfied, neither satisfied nor dissatisfied, dissatisfied |
|
|
Term
|
Definition
More response categories at one end than the other
- Unequal positive and negative categories
- Used if the issuer of the survey knows already that there is a lack of balance
- Ex) Satisfied, neither satisfied nor dissatisfied, dissatisfied, very dissatisfied |
|
|
Term
| Forced-choice Rating Scale |
|
Definition
Respondent must make a choice
- Ex) Coke is Better or Pepsi is Better |
|
|
Term
|
Definition
"No opinion" category
- Ex) Coke is Better or Pepsi is Better or They are the same |
|
|
Term
| Factors that decide if you should use a single measure or an index measure |
|
Definition
- Complexity of the issue to be investigated
- Number of dimensions the issue contains
- Whether individual attributes of the stimulus are part of a holistic attitude or are seen as separate items |
|
|
Term
| Multi-attribute Attitude Model |
|
Definition
- Belief strength
- Evaluation of attribute |
|
|
Term
| Theory of Reasoned Action |
|
Definition
Behavior expectations (expected future actions) of an individual toward an attitudinal object
- Intentions often translate into behavior
- Ex) How likely is it that you will buy a Honda?
Definitely, might, definitely will not |
|
|
