Chapter 5: Measurement Concept

Chapter 5: Measurement Concept

1.      Concept: A general idea about a group of objects, attributes or processe.Examples: satisfaction, innovativeness, materialism, media skepticism, opinion leadership.

2.   Operational Definition: Identifies what the researcher must do to measure the concept under investigation

a.       What questions must I ask to measure that concept?

Example: Media Skepticism (uncertainty) Conceptual Definition

Individual are doubtful toward the truth that is presented in the mass media. Media skepticism level is changing across people. From those who has only little doubt and accept most of what they see and hear in the media to people who completely disbelieve the facts, values of reality in the media.

Example: Media Skepticism Operational Definition

Please tell me how true each statement is about the media. Is it very true, not very true, or not at all true?

1.      The program was not very accurate in its interpretation of the problem.

2.      Most of the story was just for entertainment purposes.

3.      The presentation was unfair.

Example: Opinion Leadership Conceptual Definition

Opinion Leadership – An individual gives information about a topic and the extent to which information is wanted by others.

Example: Opinion Leadership Operational Definition

Please rate your agreement to the following statements on a scale of 1 to 7.  (1 – “strongly disagree” to 7 – “strongly agree”).

1.         My friends and neighbors often ask my advice about clothing fashions.

2.         I sometimes influence the type of clothes my friends buy.

3.         My friends come to me more often than I go to them for information about clothes.

Scale

Series of items arranged according to value for the purpose of quantification

1.      Types of Scale

                                                              i.      Nominal Scale

                                                            ii.      Ordinal Scale

                                                          iii.      Interval Scale

                                                          iv.      Ratio Scale

2.      The type of scale used will determine the form of statistical analysis

Ø  Nominal(small, insignificant) scale

Uniquely classifies

Examples:

1. “sex” where 1=male 2=female
2. “marital status” where 1=never married 2= married 3=defector
3. “yes/no type questions” where 1=yes 2=no.

Ø  Ordinal Scale Examples

1.      Uniquely classifies

2.      Preserves order

Examples:

1. “Age group” 1=under 21yrs   2=21-35yrs   3=35-49yrs   4=50 yrs and over
2. “Education” where 1=high school completed 2=tertiary studies completed 3=post-graduate studies completed.
3. The higher the value assigned, the higher the category (E.g. higher age group or education level).

Ø  Interval(gap) scale

1.      Uniquely classifies

2.      Preserves order

3.      Equal interval(gap)

Examples:

“Please rate the importance of the following attributes…” according to the scale

            1----------2----------3----------4----------5

            Where 1=strongly disagree, 2=somewhat disagree, 3=neither disagree nor agree,

4=somewhat agree, 5=strongly agree.

All Likert type scales are interval in nature.

Ø  Ratio scale example

1.      Uniquely classifies

2.      Preserves order

3.      Equal intervals

4.      Natural zero

Examples:

–        “What is your age in years?  __________years”

if the response is 8 years, then the value of 8 is assigned to that person’s age.

–        “How far in terms of meters do you walk per day?  __________meters”

If the response is 200 meters, then the value of 200 is assigned to that person.

Criteria for Good Measurement

1. Validity(power): the ability of a scale to measure what was intended to be measured
1. This relates to accuracy of the prepared definition
2. Reliability: the degree to which measures does not have any random error and therefore produce consistent results
1. This relates to consistency in interpretation of questions asked
3. Sensitivity: A measurement instrument’s ability to accurately measure unpredictability responses
1. Interval scales are more sensitive than dichotomous scales

Validity (power)

1.      Face or content: Do my measures provide adequate coverage(reporting) of the concept under investigation? Operational definition.

2.      Criterion (decisive factor) validity : Do my measures show a relationship with other accepted measures of the same concept. We need to do literature review to see how others have measured this concept.

3.      Construction validity: Do the results of my measures agree with theoretical logic? Established during statistical analysis.

Reliability

1.      Stability: retest the test: Controlling the same measures to the same subjects over time. It is used for test the stability overtime.

2.      Internal consistency

a.       Equivalent forms : Controlling 2 different sets of measure to the same subjects. High correlation means high reliability.

b.      Splitting halves

Checking the results of half the set of measures against the other half.

Attitude scaling

Attitude: A long term character to respond in a given matter consistenly.

Attitudes as theoretical create: The term hypothetical construct is used to describe a changeable that is not directly recognizable, but is measurable by an indirect means such as oral expression or open behaviour - attitudes (and other psychological variables) are considered to be such variables.

Three Components of an Attitude

1.      Affective: The feelings or emotions toward an object

2.      Cognitive: Knowledge and beliefs

3.      Behavioural: Purchase or usage intentions

Attitude measuring process

1. Ranking: Rank order preference
2. Rating: Estimates importance of a characteristic
1. Example: importance ratings, quality ratings
3. Sorting(categorised): Arrange or classify product concepts
1. Example: categorization competitors products into stacks based on their similarities
4. Choice: Selection of preferred alternative
1. Example: which of the following are you most likely to buy?

1.      Physiological measures of attitudes provide a resource of measuring attitudes without orally questioning the respondent.

2.      Example: galvanic skin responses, pupil dilations, measure blood pressure etc.

Simple Attitude Scaling

1. In its most basic form, attitude scaling requires that an individual agree with a statement to a single question. 
2. This type of self-rating scale merely classifies respondents into one of two categories

      Example: THE PRESIDENT SHOULD RUN FOR RE-ELECTION

_______ AGREE                   ______ DISAGREE

Categories scale

1.      A category scale is a more sensitive measure than a scale having only two response categories - it provides more information.

2.      Question wording is an extremely important factor in the usefulness of these scales.

Other types of Category Scales examples

1.      Quality

·         Excellent  -  Good  -  Fair  -  Poor

2.      Frequency

·         All the time  -  Very often  -  Often  -  Sometimes  -  Hardly ever

3.      Satisfaction

·         Completely  -  Somewhat  -  Neutral  -  Somewhat  -  Completely

               satisfied          satisfied                             dissatisfied     dissatisfied

Method of Summated Ratings:   The Likert Scale

1.      An extremely popular means for measuring attitudes.  Respondents indicate their own attitudes by checking how strongly they agree or disagree with statements. 

2. Response alternatives:  1=“strongly agree”, 2=“agree”, 3=“not sure”, 4=“disagree”, and 5=“strongly disagree”.

Example : Likert  Scale for Measuring Attitudes toward Tennis

1.      It is more fun to play a tough, competitive tennis match than to play an easy one.

___Strongly Agree

___Agree

___Not Sure

___Disagree

___Strongly Disagree

Semantic difference

1. A series of seven-point bipolar rating scales.  Bipolar adjectives, such as “good” and “bad”, anchor both ends (and poles) of the scale.

2.A weight is assigned to each position on the rating scale.  Traditionally, scores are 7, 6, 5, 4, 3, 2, 1, or +3, +2, +1, 0, -1, -2, -3.

Example:

Exciting                       ___ : ___ : ___ : ___ : ___ : ___ : ___   Calm

Interesting       ___ : ___ : ___ : ___ : ___ : ___ : ___   Dull

Simple                         ___ : ___ : ___ : ___ : ___ : ___ : ___   Complex

Passive            ___ : ___ : ___ : ___ : ___ : ___ : ___   Active

Numerical scale

Numerical scales have numbers as response options, rather than “semantic space’ or verbal descriptions, to identify categories (response positions).

Exciting                       7       6       5       4       3       2       1     Calm

Interesting        7       6       5       4       3       2       1     Dull

Simple                          7       6       5       4       3       2       1     Complex

Passive             7       6       5       4       3       2       1     Active

Behavioural differential

2. The behavioral differential instrument has been developed for measuring the behavioral intentions of subjects towards any object or category of objects.  A description of the object to be judged is placed on the top of a sheet, and the subjects indicate their behavioral intentions toward this object on a series of scales.
3. Example:

A 25-year old woman sales representative…

Would   ___ : ___ : ___ : ___ : ___ : ___ : ___   Would not ask this person for advice.

Staple Scales

1.      Modern versions of the Stapel scale place a single adjective as a substitute for the semantic differential when it is difficult to create pairs of bipolar adjectives.

A staple scales for measuring the store image

1.      Plus number for words that you think describe the store accurately.

2.      Select a minus number for words you think do not describe the store accurately.

Constant sum scale

Divide 100 points among each of the following brands according to your preference for the brand:

            Brand A _________

            Brand B _________

            Brand C _________

Graphic rating scale

A graphic rating scale presents respondents with a graphic continuum (scale).

Choice of Measurement Techniques

v  Ranking, Sorting, Rating, or Choice?

Ø  Ranking, sorting and choice measures yield nominal or ordinal data

Ø  Rating yields interval data

Ø  Type of data influences statistical tools

v  Monadic or Comparative Scales?

v  Balanced or Unbalanced Scales?

Monadic(single) scale

A Monadic Rating Scale asks about a single concept

Example:

Now that you’ve had your automobile for about 1 year, please tell us how satisfied you are with its engine power and pickup.

             5                 4                 3                 2                  1

      Completely       Very             Fairly Well       Somewhat         Very

            Satisfied           Satisfied       Satisfied          Dissatisfied       Dissatisfied

Comparative scale

A Comparative Rating Scale asks respondents to rate a concept by comparing it with a level

Example:

Please indicate how the amount of authority in your present position compares with the    amount of authority that would be ideal for this position.

                   3                                   2                                  1

            TOO MUCH                      ABOUT RIGHT                      TOO LITTLE

An unbalanced scale

An Unbalanced Scale has more responses distributed at one end of the scale

For example :

How satisfied are you with the bookstore in the Student Union?

      4                                  3                       2                           1

                          Neither Satisfied           Quite                     Very

Satisfied           Nor Dissatisfied            Dissatisfied           Dissatisfied