measurement scales 指導教授:洪新原 教授 603530042 張顥獻 603530044 蔡毓萍
TRANSCRIPT
Measurement Scales
指導教授:洪新原 教授
603530042 張顥獻603530044 蔡毓萍
2 /54
Catalog
The nature of attitude Selecting a measurement scale Rating scales Ranking scales Sorting Cumulative scales
3 /54
Learning objective
The nature of attitudes and their relationship to behavior.
The critical decisions involved in selecting an appropriate measurement scale.
The characteristics and use of rating, ranking, sorting, and other preference scales.
4 /54
The scaling
process
5 /54
The nature of attitudes
The relationship between Attitudes and Behavior
Attitude scaling
6 /54
The nature of attitudes
What is attitude?
Attitude is a learned stable predisposition to respond to oneself, other persons, object, or issues in a consistently favorable or unfavorable way.
7 /54
CognitiveI think oatmeal is healthier
than corn flakes for breakfast.
Affective
Behavioral
I hate corn flakes.
I intend to eat more oatmealfor breakfast.
The nature of attitudes
8 /54
The relationship between Attitudes and Behavior The attitude-behavior relationship is not
straightforward, although there may be close linkage
Attitudes don’t always lead to actual behaviors
Sometimes behaviors can influence attitudes
9 /54
Factors affect the attitude research
Specific attitudes
Strong attitudes
Experiences
Cognitive-based better than affective-based
10 /54
Factors affect the attitude research
Affective-based better predict consumption behaviors
Multiple measurements across time and environments
The influence of group and individual’s inclination
11 /54
Attitude scaling
ScalingProcedure for the assignment of numbers to
a property of objects in order to impact some of the characteristics of numbers to the properties in question.
ExampleThermometer
12 /54
Selecting a measurement scale
Research objective Response types Data properties Number of dimensions Balanced or unbalanced Forced or unforced choices Number of scale points Rater errors
13 /54
Research objectives
Too numerous to list
But here are two general typesMeasure characteristics of the participantsUse participants as judges of the objects
14 /54
Response types
Rating scaleParticipants score an object without making a
comparison to another object
Ranking scaleConstrain the participant to making
comparisons and determining order among properties
15 /54
Response types
CategorizationParticipants put themselves or property
indicants in group or categories
SortingParticipants sort cards into piles using criteria
established by the researcher
16 /54
Data properties
Nominal scale Classify data into categories
Ordinal scale Show the relationships of more or less than
Interval scale With the distance relationship
Ratio scale Possess the above properties
17 /54
Number of dimensions
Unidimensional scaleOne seeks to measure only one attribute of th
e participants or objects
Multidimensional scaleBetter describe an object with several dimensi
ons than unidimensional scale
18 /54
Balanced or unbalanced
Balanced rating scale An equal number of categories above and below the
midpoint
Unbalanced rating scale An unequal number of favorable and unfavorable
response choices Expect the mean rating will be near one side Avoid the error of leniency
19 /54
Very bad
Bad
Neither good nor bad
Good
Very good
Poor
Fair
Good
Very good
Excellent
How good an actress is Jennifer Lawrence?
Balanced or unbalanced
20 /54
Forced or Unforced choice
Unforced-choice rating scaleProvide participants with an opportunity to
express no opinion
Forced-choice rating scaleRequires participants select one of the
offered alternativeMay cause some error of the result
21 /54
Very bad
Bad
Neither good nor bad
Good
Very good
Very bad
Bad
Neither good nor bad
Good
Very good
No opinion
How good an actress is Jennifer Lawrence?
Forced or Unforced choice
22 /54
Number of scale points
What is the ideal number of points?A scale should be appropriate for its purpose
Easy to make decisionSimple scale
The object is complex or importantMore scale points
23 /54
Number of scale points
The reliability increases if the number of scale points increases
Much more number of scale points may produce more valid results
To extract more variance
Produce accuracy when using Unidimensional scale
The cultural practices may condition participants to a standard metric
24 /54
Rater errors
Error of central tendencySome raters reluctant to give extreme
judgments
Error of leniency
25 /54
Rater errors
To address the tendencies Adjust the strength of descriptive adjectives
Space the intermediate descriptive phrases farther apart
Provide smaller differences in meaning between the steps near the ends of the scale than between the steps near the center
Use more points in the scale
26 /54
Rater errors
Halo effect A systematic bias that the rater introduces by carrying
over a generalized impression of the subject from one rating to another
To avoid halo effect Participant rate one trait at a time Revealing one trait per page Reverse anchors periodically
27 /54
Rating Scales
Simple attitude scale Likert scales Semantic differential scales Numerical scales Multiple rating list scales Stapel scales Constant-sum scales Graphic rating scales
28 /54
The simple category scale(also called a dichotomous scale) offers two mutually exclusive response choice.
I plan to purchase a MindWriter laptop in the next 12 months. Yes No
Simple Attitude Scale
29 /54
Simple Attitude Scale
When there are multiple options for the rater but only one answer is sought, the multiple-choice, single-response scale is appropriate.
What newspaper do you read most often for financial news? East City Gazette West City Tribune Regional newspaper National newspaper Other (specify:_________)
30 /54
Simple Attitude Scale
The multiple-choice, multiple-response scale(also called a checklist), allows the rater to select one or several alternatives.
Check any of the sources you consulted when designing your new home. Online planning services Magazines Independent contractor/builder Designer Architect Other (specify:_______)
31 /54
Likert scale
The Likert scale, is the most frequently used variation of the summated rating scale.
The participant is asked to agree or disagree with each statement.
Each response is given a numerical score to reflect its degree of attitudinal favorableness.
32 /54
Likert scale
The Internet is superior to traditional libraries for comprehensive searches.
Strongly Disagree Disagree Neither Agree nor Disagree Agree Strongly Agree
33 /54
Likert scale
The two extreme groups represent people with the most favorable and least favorable attitudes toward the attitude being studied.
Item analysis: It involves calculating the mean scores for each
scale item among the low scores and high scorers. The mean scores for the high-score and low-score
groups are then tested for statistical significance by computing t values.
34 /54
Semantic differential scale
Semantic differential scale measures the psychological meanings of an attitude object using bipolar adjectives.
35 /54
Semantic differential scale
Osgood and his associates produced a list of 289 bipolar adjective pairs, which were reduced to 76pairs and formed into rating scales for attitude research.
There factors contributed most to meaningful judgments by participants: Evaluation (E)Potency (P)Activity (A)
36 /54
Evaluation (E) Potency (P) Activity (A)
good—bad Hard—soft Active—passive
Positive—negative Strong—weak Fast—slow
Optimistic—pessimistic Heavy—light Hot—cold
Complete—incomplete Masculine—feminine Excitable--calm
Time—untimely Severe—lenient
Tenacious—yielding
• Result of the thesaurus study
37 /54
Semantic differential scale
Steps in constructing an SD scale
38 /54
About step2…..
39 /54
Semantic differential scale
SD Scale for Analyzing industry Association Candidates
40 /54
Semantic differential scale
The data are plotted in a “snake diagram”
41 /54
Numerical Scale
Numerical Scale have equal intervals that separate their numeric scale points.
Numerical scales are often 5-point scales. The participants write a number from the
scale next to each item.
42 /54
Multiple Rating List Scale
It is similar to the numerical scale but differs in two ways: It accepts a circled response from the rater.The layout facilitates visualization of the result
s.“Please indicate how important or unimportant each service characteristic is:”
IMPORTANT UNIMPORTANTFast, reliable repair 7 6 5 4 3 2 1Service at my location 7 6 5 4 3 2 1Maintenance by manufacturer 7 6 5 4 3 2 1Knowledgeable technicians 7 6 5 4 3 2 1Notification of upgrades 7 6 5 4 3 2 1Service contract after warranty 7 6 5 4 3 2 1
43 /54
Stapel Scales
Stapel scales is used as an alternative to the semantic differential, especially when it is difficult to find bipolar adjectives that match the investigative question.
44 /54
Constant-sum scale
A scale that helps the researcher discover proportions is the constant-sum scale.
The participant allocates point to more than one attribute or property indicant, such that they total a constant sum, usually 100 or 10.
You have 100 points to distribute among the following characteristics of the Dallas Steakhouse Indicate the relative importance of each attribute:
____Food Quality____Atmosphere____Service____Price100 TOTAL
45 /54
Graphic Rating Scales
it was originally created to enable researchers to discern fine differences.
They are instructed to mark their response at any point along a continuum.
Usually, the score is a measure of length from either endpoint.
Never X Always
46 /54
Ranking Scales
Paired-comparison scale Forced ranking scale Comparative scale
47 /54
Paired-Comparison Scale
paired-comparison scale, the participant can express attitudes unambiguously by choosing between two objects.
The number of judgments required in a paired comparison is [(n)(n-1)/2], where n is the number of stimuli or objects to be judged.
48 /54
Forced Ranking Scale
It lists attributes that are ranked relative to each other.
This method is faster than paired comparisons and is usually easier and more motivating to the participant.
49 /54
Comparative scale
This calls for a standard by which other programs, processes, brands, point-of –sale promotions, or people can be compared.
50 /54
Sorting
Q-sorts
51 /54
Q-sort
Q-sorts require sorting of a deck of cards into piles that represent points along a continuum.
The participant groups the cards based on his response to the concept written on the card.
52 /54
Cumulative Scales
Total scores on cumulative scales have the same meaning.
Given a person’s total score, it is possible to estimate which items were answered positively and negatively.
53 /54
Cumulative Scales
Scalogram analysis is a procedure for determining whether a set of items forms a unidimensional scale.
Item
Participant Score
2 4 1 3
X X X X 4__ X X X 3__ __ X X 2__ __ __ X 1__ __ __ __ 0
* X = agree; __ = disagree.
54 /54
Thanks for listening