PS11A Psychology Laboratory

1
PS11A Psychology Laboratory Methods Abnormal,
Social Developmental

• Charlene Coore
• 2006-2007

2
Scaling

• Scaling creates an ordinal, interval or ratio
  measure of a variable expressed as a numerical
  score.
• Scales are commonly used in situations where a
  researcher wants to measure how an individual
  feels or thinks about something.

3
Commonly Used Scales

• Likert scales
• Thurstone scales
• Bogardus Social Distance scales
• Semantic Differential
• Guttman Scaling

4
Likert Scales

• Developed in the 1930s by Rensis Likert to
  provide an ordinal measure of a persons
  attitude.
• This scale is a summed-rating or an additive
  scale because a persons score on the rating
  scale is computed by summing the number of
  responses the person gives.
• Usually 4-8 categories (more than 8 categories is
  probably not meaningful).

5
Likert Scale

• The Neutral category. (e.g. dont know,
  undecided or no opinion.)
• Sometimes questions are phrased in the reverse to
  avoid the problem of a response set/response
  style/response bias.

6
Likert Scale

• E.g. Rosenberg Self-Esteem scale
• All in all I am inclined to feel that I am a
  failure
• I think that I can do things as well as most
  other people. 
• Remember these are Ordinal Scales!

7
Thurstone Scaling

• Based on the law of the comparative judgement.
  The law addresses the issue of measuring or
  comparing attitudes when each person makes a
  unique judgement.
• It anchors or fixes the position of one persons
  attitudes relative to that of others as each
  makes an individual subjective judgement.

8
Example of Thurstone Scaling

• Variable Measured Opinion with regard to death
  penalty.
• Step 1 Develop 120 statements about the death
  penalty using personal experience, the popular
  and professional literature and listening to
  others.
•  

9
Thurstone Scaling

• Example statements
• I think that the death penalty is cruel and
  unusual punishment.
• Without the death penalty, there would be many
  more violent crimes.
• I believe that the death penalty should be used
  for only very violent crimes.
•  

10
Thurstone Scaling

• Step 2 Place each statement on a separate card
  or sheet of paper and make 100 sets of the 120
  statements.
• Step 3 Locate 100 persons who agree to serve as
  judges. Give each judge a set of statements and
  instructions to place them in one of the 11 piles
  from 1 highly unfavourable statement to 11
  highly favourable statement.

11
Thurstone Scaling

• Step 4 The judges place each statement into one
  of the 11 piles (example judge 1 puts statement
  1 into pile 3 and judge 2 puts statement 1 in
  pile 7.)
• Step 5 Collect piles from judges and create a
  chart summarizing their responses

12
CHART Number of judges rating each statement
rating pile
Unfavourable Favourable
1 2 3 4 5
6 7 8 9
10 11 Total ________________________
__________________________________________________
___________ Statement 1 23 60 12
5 0 0 0
0 0 0 0
100   2 0 0 0
0 2 12 18 41
19 8 0 100   3 2
8 7 13 31
19 12 6 2
0 0 100
13
Thurstone Scaling

• Step 6 Compute the average rating and degree of
  agreement by the judges. For example in question
  1 there is high agreement as opposed to question
  3 which has much less agreement
• Step 7 Choose the final 20 to include in the
  death penalty questionnaire.
• Step 8 Prepare a 20-statement questionnaire,
  and ask people in a study whether they agree or
  disagree with the statement.

14
 Bogardus Social Distance Scale

• It measures the distance that respondents
  perceive between themselves and members of
  different social categories

15
Example of Bogardus

• People are given a series of statements
• People from group X are entering your country
• People from group X are in your town
• People from group X are at your workplace
• People from group X live in your neighbourhood
• People from group X become your personal friends
• People from group X marry your bro or sis

16
Bogardus Social Distance Scale

• Respondents are asked whether they feel
  comfortable with the statement or if the contact
  is acceptable.
• They can also be asked to keep reading the
  statements until they are not comfortable anymore
  with a relationship.
• There is no set number of statements that can be
  asked but it is usually between 5 9.

17
Semantic Differential

• This scale was developed in the 1950s to provide
  an indirect measure of how a person feels about a
  concept, object or other persons.
• It measures subjective feelings toward something
  using adjectives. It uses polar opposite
  adjectives to create a rating measure or scale.
  Polar opposites (strong/weak good/bad).

18
Guttman Scaling

• It was created by Louis Guttman in the 1940s to
  determine whether a relationship existed among a
  set indicators or measurement items.
• Some items on the scale are more extreme
  indicators of whatever your trying to measure.

19
Guttman Scaling

• Measuring a set of indicators or items
• Usually measured as a simple yes/no
• 3-20 indicators can be used
• The scale places the results into a Guttman scale
  and determines whether the items form a pattern
  that corresponds to the relationship.

20
Guttman Scale

• E.g. Clogg and Sawyer (1981) used the Guttman
  scale to look at US attitudes towards abortion.
• Choice 1 If the mothers life is in danger 92
• Choice 2 Pregnant as the result of rape 86
• Choice 3 Not married 48

21
Guttman Scaling

• Choice number 3 is the strongest measure of a
  belief in the womans right to an abortion.
• Choice number 1 is not a good measure because
  almost everyone agreed with it
• The logical relationship among items in a Guttman
  scaling is hierarchical. The smaller number of
  cases that have higher-order items also have
  lower order ones but not vice versa. The items
  are scalable