Scaling and Multiple Item Measures

1
Scaling and Multiple Item Measures
2
Levels of Measurement

• Remember
• nominal
• ordinal
• interval
• ratio

3
Nominal

• Number of CasesMode
• Religious groups
• Qualities

4
Ordinal

• Median, percentiles
• Likeability, pleasantness of food
• For example, on a survey you might code
  Educational Attainment as 0less than H.S.
  1some H.S. 2H.S. degree 3some college
  4college degree 5post college. In this
  measure, higher numbers mean more education. But
  is distance from 0 to 1 same as 3 to 4? Of course
  not. The interval between values is not
  interpretable in an ordinal measure.

5
Interval

• Mean, Standard Deviation, Correlation
• Temperature, Calendar dates
• In interval measurement the distance between
  attributes does have meaning. For example, when
  we measure temperature (in Fahrenheit), the
  distance from 30-40 is same as distance from
  70-80. The interval between values is
  interpretable. Because of this, it makes sense to
  compute an average of an interval variable, where
  it doesn't make sense to do so for ordinal
  scales. But note that in interval measurement
  ratios don't make any sense - 80 degrees is not
  twice as hot as 40 degrees (although the
  attribute value is twice as large).

6
Ratio

• Weight is a ratio variable. In applied social
  research most "count" variables are ratio, for
  example, the number of clients in past six
  months. Why? Because you can have zero clients
  and because it is meaningful to say that "...we
  had twice as many clients in the past six months
  as we did in the previous six months."

7
Types of Scales

• Graphic
• Feeling thermometer
• Itemized
• extremely healthyhealthy..not healthy.
• Comparative
• As compared to others.how do you rate ???

8
Cautions

• Halo bias
• Overall positive/negative
• Generosity
• Contrast Error

9
Selecting Items

• Criteria
• Face (logical) validity
• Unidimensionality
• General or specific
• Variance

10
Empirical Relationships

• Established when respondents answers to a
  question help predict how they will answer other
  questions.
• If two items are empirically related, we can
  argue that each reflects the same variable, and
  both can be included in the same index.
• Bivariate relationships - relationships between
  2 variables.
• Multivariate relationships - relationship
  between more than 2 variables.

11
Assign Scores for Responses

• Two basic decisions
• Decide the desirable range of the scores.
• Decide whether to give each item equal weight or
  different weights.

12
Techniques of Scale Construction

• Thurstone scales - judges determine the intensity
  of different indicators. Assumes people will
  agree with only one position on an attitude
  dimension and disagree with other items in either
  direction http//www.socialresearchmethods.net/kb/
  scalthur.htm
• .
• Bogardus social distance scale - measures the
  willingness of people to participate in social
  relationshttp//gwbweb.wustl.edu/CMHSR/measure/k19
  .html

13
Techniques of Scale Construction

• Likert scaling - uses standardized response
  categories.
• Semantic differential -asks respondents to rank
  answers between two extremes.
• Guttman scaling - uses an empirical intensity
  structure (most common). http//www.socialresearch
  methods.net/kb/scalgutt.htm

14
Example of a Likert Scale

• http//www.socialresearchmethods.net/kb/scallik.ht
  m

15
Scales and Screening

• ASDS (Aspergers Syndrome Disorder Screen)
• MSI-R (Marital Satifaction Inventory-R)